Adding who terminal translate (#264)
* Update README.md * Spelling fixes * Update hardware.md * Adding IoT for beginners episode * Adding intro video * Fixing formatting of read more and self study sections. * Adding instructions for installing the ReSpeaker * Adding auth to language understanding * Adding Wio terminal timer setting * Update config.h * Fixing links and images * Increasing version numbers for SD card fix * Adding SD card requirement * speech and translations * Adding more on translations * All Wio Terminal now working except playing audiopull/268/head
parent
9cd654d298
commit
395a23b346
@ -0,0 +1,26 @@
|
||||
import json
|
||||
import os
|
||||
import requests
|
||||
|
||||
import azure.functions as func
|
||||
|
||||
def main(req: func.HttpRequest) -> func.HttpResponse:
|
||||
location = os.environ['SPEECH_LOCATION']
|
||||
speech_key = os.environ['SPEECH_KEY']
|
||||
|
||||
req_body = req.get_json()
|
||||
language = req_body['language']
|
||||
|
||||
url = f'https://{location}.tts.speech.microsoft.com/cognitiveservices/voices/list'
|
||||
|
||||
headers = {
|
||||
'Ocp-Apim-Subscription-Key': speech_key
|
||||
}
|
||||
|
||||
response = requests.get(url, headers=headers)
|
||||
voices_json = json.loads(response.text)
|
||||
|
||||
voices = filter(lambda x: x['Locale'].lower() == language.lower(), voices_json)
|
||||
voices = map(lambda x: x['ShortName'], voices)
|
||||
|
||||
return func.HttpResponse(json.dumps(list(voices)), status_code=200)
|
@ -0,0 +1,20 @@
|
||||
{
|
||||
"scriptFile": "__init__.py",
|
||||
"bindings": [
|
||||
{
|
||||
"authLevel": "function",
|
||||
"type": "httpTrigger",
|
||||
"direction": "in",
|
||||
"name": "req",
|
||||
"methods": [
|
||||
"get",
|
||||
"post"
|
||||
]
|
||||
},
|
||||
{
|
||||
"type": "http",
|
||||
"direction": "out",
|
||||
"name": "$return"
|
||||
}
|
||||
]
|
||||
}
|
@ -0,0 +1,15 @@
|
||||
{
|
||||
"version": "2.0",
|
||||
"logging": {
|
||||
"applicationInsights": {
|
||||
"samplingSettings": {
|
||||
"isEnabled": true,
|
||||
"excludedTypes": "Request"
|
||||
}
|
||||
}
|
||||
},
|
||||
"extensionBundle": {
|
||||
"id": "Microsoft.Azure.Functions.ExtensionBundle",
|
||||
"version": "[2.*, 3.0.0)"
|
||||
}
|
||||
}
|
@ -0,0 +1,12 @@
|
||||
{
|
||||
"IsEncrypted": false,
|
||||
"Values": {
|
||||
"FUNCTIONS_WORKER_RUNTIME": "python",
|
||||
"AzureWebJobsStorage": "",
|
||||
"LUIS_KEY": "<primary key>",
|
||||
"LUIS_ENDPOINT_URL": "<endpoint url>",
|
||||
"LUIS_APP_ID": "<app id>",
|
||||
"SPEECH_KEY": "<key>",
|
||||
"SPEECH_LOCATION": "<location>"
|
||||
}
|
||||
}
|
@ -0,0 +1,5 @@
|
||||
# Do not include azure-functions-worker as it may conflict with the Azure Functions platform
|
||||
|
||||
azure-functions
|
||||
azure-cognitiveservices-language-luis
|
||||
librosa
|
@ -0,0 +1,52 @@
|
||||
import io
|
||||
import os
|
||||
import requests
|
||||
|
||||
import librosa
|
||||
import soundfile as sf
|
||||
import azure.functions as func
|
||||
|
||||
location = os.environ['SPEECH_LOCATION']
|
||||
speech_key = os.environ['SPEECH_KEY']
|
||||
|
||||
def get_access_token():
|
||||
headers = {
|
||||
'Ocp-Apim-Subscription-Key': speech_key
|
||||
}
|
||||
|
||||
token_endpoint = f'https://{location}.api.cognitive.microsoft.com/sts/v1.0/issuetoken'
|
||||
response = requests.post(token_endpoint, headers=headers)
|
||||
return str(response.text)
|
||||
|
||||
playback_format = 'riff-48khz-16bit-mono-pcm'
|
||||
|
||||
def main(req: func.HttpRequest) -> func.HttpResponse:
|
||||
req_body = req.get_json()
|
||||
language = req_body['language']
|
||||
voice = req_body['voice']
|
||||
text = req_body['text']
|
||||
|
||||
url = f'https://{location}.tts.speech.microsoft.com/cognitiveservices/v1'
|
||||
|
||||
headers = {
|
||||
'Authorization': 'Bearer ' + get_access_token(),
|
||||
'Content-Type': 'application/ssml+xml',
|
||||
'X-Microsoft-OutputFormat': playback_format
|
||||
}
|
||||
|
||||
ssml = f'<speak version=\'1.0\' xml:lang=\'{language}\'>'
|
||||
ssml += f'<voice xml:lang=\'{language}\' name=\'{voice}\'>'
|
||||
ssml += text
|
||||
ssml += '</voice>'
|
||||
ssml += '</speak>'
|
||||
|
||||
response = requests.post(url, headers=headers, data=ssml.encode('utf-8'))
|
||||
|
||||
raw_audio, sample_rate = librosa.load(io.BytesIO(response.content), sr=48000)
|
||||
resampled = librosa.resample(raw_audio, sample_rate, 44100)
|
||||
|
||||
output_buffer = io.BytesIO()
|
||||
sf.write(output_buffer, resampled, 44100, 'PCM_16', format='wav')
|
||||
output_buffer.seek(0)
|
||||
|
||||
return func.HttpResponse(output_buffer.read(), status_code=200)
|
@ -0,0 +1,20 @@
|
||||
{
|
||||
"scriptFile": "__init__.py",
|
||||
"bindings": [
|
||||
{
|
||||
"authLevel": "function",
|
||||
"type": "httpTrigger",
|
||||
"direction": "in",
|
||||
"name": "req",
|
||||
"methods": [
|
||||
"get",
|
||||
"post"
|
||||
]
|
||||
},
|
||||
{
|
||||
"type": "http",
|
||||
"direction": "out",
|
||||
"name": "$return"
|
||||
}
|
||||
]
|
||||
}
|
@ -0,0 +1,46 @@
|
||||
import logging
|
||||
|
||||
import azure.functions as func
|
||||
import json
|
||||
import os
|
||||
from azure.cognitiveservices.language.luis.runtime import LUISRuntimeClient
|
||||
from msrest.authentication import CognitiveServicesCredentials
|
||||
|
||||
|
||||
def main(req: func.HttpRequest) -> func.HttpResponse:
|
||||
luis_key = os.environ['LUIS_KEY']
|
||||
endpoint_url = os.environ['LUIS_ENDPOINT_URL']
|
||||
app_id = os.environ['LUIS_APP_ID']
|
||||
|
||||
credentials = CognitiveServicesCredentials(luis_key)
|
||||
client = LUISRuntimeClient(endpoint=endpoint_url, credentials=credentials)
|
||||
|
||||
req_body = req.get_json()
|
||||
text = req_body['text']
|
||||
logging.info(f'Request - {text}')
|
||||
prediction_request = { 'query' : text }
|
||||
|
||||
prediction_response = client.prediction.get_slot_prediction(app_id, 'Staging', prediction_request)
|
||||
|
||||
if prediction_response.prediction.top_intent == 'set timer':
|
||||
numbers = prediction_response.prediction.entities['number']
|
||||
time_units = prediction_response.prediction.entities['time unit']
|
||||
total_seconds = 0
|
||||
|
||||
for i in range(0, len(numbers)):
|
||||
number = numbers[i]
|
||||
time_unit = time_units[i][0]
|
||||
|
||||
if time_unit == 'minute':
|
||||
total_seconds += number * 60
|
||||
else:
|
||||
total_seconds += number
|
||||
|
||||
logging.info(f'Timer required for {total_seconds} seconds')
|
||||
|
||||
payload = {
|
||||
'seconds': total_seconds
|
||||
}
|
||||
return func.HttpResponse(json.dumps(payload), status_code=200)
|
||||
|
||||
return func.HttpResponse(status_code=404)
|
@ -0,0 +1,20 @@
|
||||
{
|
||||
"scriptFile": "__init__.py",
|
||||
"bindings": [
|
||||
{
|
||||
"authLevel": "function",
|
||||
"type": "httpTrigger",
|
||||
"direction": "in",
|
||||
"name": "req",
|
||||
"methods": [
|
||||
"get",
|
||||
"post"
|
||||
]
|
||||
},
|
||||
{
|
||||
"type": "http",
|
||||
"direction": "out",
|
||||
"name": "$return"
|
||||
}
|
||||
]
|
||||
}
|
@ -0,0 +1,39 @@
|
||||
|
||||
This directory is intended for project header files.
|
||||
|
||||
A header file is a file containing C declarations and macro definitions
|
||||
to be shared between several project source files. You request the use of a
|
||||
header file in your project source file (C, C++, etc) located in `src` folder
|
||||
by including it, with the C preprocessing directive `#include'.
|
||||
|
||||
```src/main.c
|
||||
|
||||
#include "header.h"
|
||||
|
||||
int main (void)
|
||||
{
|
||||
...
|
||||
}
|
||||
```
|
||||
|
||||
Including a header file produces the same results as copying the header file
|
||||
into each source file that needs it. Such copying would be time-consuming
|
||||
and error-prone. With a header file, the related declarations appear
|
||||
in only one place. If they need to be changed, they can be changed in one
|
||||
place, and programs that include the header file will automatically use the
|
||||
new version when next recompiled. The header file eliminates the labor of
|
||||
finding and changing all the copies as well as the risk that a failure to
|
||||
find one copy will result in inconsistencies within a program.
|
||||
|
||||
In C, the usual convention is to give header files names that end with `.h'.
|
||||
It is most portable to use only letters, digits, dashes, and underscores in
|
||||
header file names, and at most one dot.
|
||||
|
||||
Read more about using header files in official GCC documentation:
|
||||
|
||||
* Include Syntax
|
||||
* Include Operation
|
||||
* Once-Only Headers
|
||||
* Computed Includes
|
||||
|
||||
https://gcc.gnu.org/onlinedocs/cpp/Header-Files.html
|
@ -0,0 +1,46 @@
|
||||
|
||||
This directory is intended for project specific (private) libraries.
|
||||
PlatformIO will compile them to static libraries and link into executable file.
|
||||
|
||||
The source code of each library should be placed in a an own separate directory
|
||||
("lib/your_library_name/[here are source files]").
|
||||
|
||||
For example, see a structure of the following two libraries `Foo` and `Bar`:
|
||||
|
||||
|--lib
|
||||
| |
|
||||
| |--Bar
|
||||
| | |--docs
|
||||
| | |--examples
|
||||
| | |--src
|
||||
| | |- Bar.c
|
||||
| | |- Bar.h
|
||||
| | |- library.json (optional, custom build options, etc) https://docs.platformio.org/page/librarymanager/config.html
|
||||
| |
|
||||
| |--Foo
|
||||
| | |- Foo.c
|
||||
| | |- Foo.h
|
||||
| |
|
||||
| |- README --> THIS FILE
|
||||
|
|
||||
|- platformio.ini
|
||||
|--src
|
||||
|- main.c
|
||||
|
||||
and a contents of `src/main.c`:
|
||||
```
|
||||
#include <Foo.h>
|
||||
#include <Bar.h>
|
||||
|
||||
int main (void)
|
||||
{
|
||||
...
|
||||
}
|
||||
|
||||
```
|
||||
|
||||
PlatformIO Library Dependency Finder will find automatically dependent
|
||||
libraries scanning project source files.
|
||||
|
||||
More information about PlatformIO Library Dependency Finder
|
||||
- https://docs.platformio.org/page/librarymanager/ldf.html
|
@ -0,0 +1,23 @@
|
||||
; PlatformIO Project Configuration File
|
||||
;
|
||||
; Build options: build flags, source filter
|
||||
; Upload options: custom upload port, speed and extra flags
|
||||
; Library options: dependencies, extra library storages
|
||||
; Advanced options: extra scripting
|
||||
;
|
||||
; Please visit documentation for the other options and examples
|
||||
; https://docs.platformio.org/page/projectconf.html
|
||||
|
||||
[env:seeed_wio_terminal]
|
||||
platform = atmelsam
|
||||
board = seeed_wio_terminal
|
||||
framework = arduino
|
||||
lib_deps =
|
||||
seeed-studio/Seeed Arduino FS @ 2.1.1
|
||||
seeed-studio/Seeed Arduino SFUD @ 2.0.2
|
||||
seeed-studio/Seeed Arduino rpcWiFi @ 1.0.5
|
||||
seeed-studio/Seeed Arduino rpcUnified @ 2.1.3
|
||||
seeed-studio/Seeed_Arduino_mbedtls @ 3.0.1
|
||||
seeed-studio/Seeed Arduino RTC @ 2.0.0
|
||||
bblanchon/ArduinoJson @ 6.17.3
|
||||
contrem/arduino-timer @ 2.3.0
|
@ -0,0 +1,93 @@
|
||||
#pragma once
|
||||
|
||||
#define RATE 16000
|
||||
#define SAMPLE_LENGTH_SECONDS 4
|
||||
#define SAMPLES RATE * SAMPLE_LENGTH_SECONDS
|
||||
#define BUFFER_SIZE (SAMPLES * 2) + 44
|
||||
#define ADC_BUF_LEN 1600
|
||||
|
||||
const char *SSID = "<SSID>";
|
||||
const char *PASSWORD = "<PASSWORD>";
|
||||
|
||||
const char *SPEECH_API_KEY = "<API_KEY>";
|
||||
const char *SPEECH_LOCATION = "<LOCATION>";
|
||||
const char *LANGUAGE = "<LANGUAGE>";
|
||||
|
||||
const char *TOKEN_URL = "https://%s.api.cognitive.microsoft.com/sts/v1.0/issuetoken";
|
||||
const char *SPEECH_URL = "https://%s.stt.speech.microsoft.com/speech/recognition/conversation/cognitiveservices/v1?language=%s";
|
||||
|
||||
const char *TEXT_TO_TIMER_FUNCTION_URL = "http://<IP_ADDRESS>:7071/api/text-to-timer";
|
||||
const char *GET_VOICES_FUNCTION_URL = "http://<IP_ADDRESS>:7071/api/get-voices";
|
||||
const char *TEXT_TO_SPEECH_FUNCTION_URL = "http://<IP_ADDRESS>:7071/api/text-to-speech";
|
||||
|
||||
const char *TOKEN_CERTIFICATE =
|
||||
"-----BEGIN CERTIFICATE-----\r\n"
|
||||
"MIIF8zCCBNugAwIBAgIQAueRcfuAIek/4tmDg0xQwDANBgkqhkiG9w0BAQwFADBh\r\n"
|
||||
"MQswCQYDVQQGEwJVUzEVMBMGA1UEChMMRGlnaUNlcnQgSW5jMRkwFwYDVQQLExB3\r\n"
|
||||
"d3cuZGlnaWNlcnQuY29tMSAwHgYDVQQDExdEaWdpQ2VydCBHbG9iYWwgUm9vdCBH\r\n"
|
||||
"MjAeFw0yMDA3MjkxMjMwMDBaFw0yNDA2MjcyMzU5NTlaMFkxCzAJBgNVBAYTAlVT\r\n"
|
||||
"MR4wHAYDVQQKExVNaWNyb3NvZnQgQ29ycG9yYXRpb24xKjAoBgNVBAMTIU1pY3Jv\r\n"
|
||||
"c29mdCBBenVyZSBUTFMgSXNzdWluZyBDQSAwNjCCAiIwDQYJKoZIhvcNAQEBBQAD\r\n"
|
||||
"ggIPADCCAgoCggIBALVGARl56bx3KBUSGuPc4H5uoNFkFH4e7pvTCxRi4j/+z+Xb\r\n"
|
||||
"wjEz+5CipDOqjx9/jWjskL5dk7PaQkzItidsAAnDCW1leZBOIi68Lff1bjTeZgMY\r\n"
|
||||
"iwdRd3Y39b/lcGpiuP2d23W95YHkMMT8IlWosYIX0f4kYb62rphyfnAjYb/4Od99\r\n"
|
||||
"ThnhlAxGtfvSbXcBVIKCYfZgqRvV+5lReUnd1aNjRYVzPOoifgSx2fRyy1+pO1Uz\r\n"
|
||||
"aMMNnIOE71bVYW0A1hr19w7kOb0KkJXoALTDDj1ukUEDqQuBfBxReL5mXiu1O7WG\r\n"
|
||||
"0vltg0VZ/SZzctBsdBlx1BkmWYBW261KZgBivrql5ELTKKd8qgtHcLQA5fl6JB0Q\r\n"
|
||||
"gs5XDaWehN86Gps5JW8ArjGtjcWAIP+X8CQaWfaCnuRm6Bk/03PQWhgdi84qwA0s\r\n"
|
||||
"sRfFJwHUPTNSnE8EiGVk2frt0u8PG1pwSQsFuNJfcYIHEv1vOzP7uEOuDydsmCjh\r\n"
|
||||
"lxuoK2n5/2aVR3BMTu+p4+gl8alXoBycyLmj3J/PUgqD8SL5fTCUegGsdia/Sa60\r\n"
|
||||
"N2oV7vQ17wjMN+LXa2rjj/b4ZlZgXVojDmAjDwIRdDUujQu0RVsJqFLMzSIHpp2C\r\n"
|
||||
"Zp7mIoLrySay2YYBu7SiNwL95X6He2kS8eefBBHjzwW/9FxGqry57i71c2cDAgMB\r\n"
|
||||
"AAGjggGtMIIBqTAdBgNVHQ4EFgQU1cFnOsKjnfR3UltZEjgp5lVou6UwHwYDVR0j\r\n"
|
||||
"BBgwFoAUTiJUIBiV5uNu5g/6+rkS7QYXjzkwDgYDVR0PAQH/BAQDAgGGMB0GA1Ud\r\n"
|
||||
"JQQWMBQGCCsGAQUFBwMBBggrBgEFBQcDAjASBgNVHRMBAf8ECDAGAQH/AgEAMHYG\r\n"
|
||||
"CCsGAQUFBwEBBGowaDAkBggrBgEFBQcwAYYYaHR0cDovL29jc3AuZGlnaWNlcnQu\r\n"
|
||||
"Y29tMEAGCCsGAQUFBzAChjRodHRwOi8vY2FjZXJ0cy5kaWdpY2VydC5jb20vRGln\r\n"
|
||||
"aUNlcnRHbG9iYWxSb290RzIuY3J0MHsGA1UdHwR0MHIwN6A1oDOGMWh0dHA6Ly9j\r\n"
|
||||
"cmwzLmRpZ2ljZXJ0LmNvbS9EaWdpQ2VydEdsb2JhbFJvb3RHMi5jcmwwN6A1oDOG\r\n"
|
||||
"MWh0dHA6Ly9jcmw0LmRpZ2ljZXJ0LmNvbS9EaWdpQ2VydEdsb2JhbFJvb3RHMi5j\r\n"
|
||||
"cmwwHQYDVR0gBBYwFDAIBgZngQwBAgEwCAYGZ4EMAQICMBAGCSsGAQQBgjcVAQQD\r\n"
|
||||
"AgEAMA0GCSqGSIb3DQEBDAUAA4IBAQB2oWc93fB8esci/8esixj++N22meiGDjgF\r\n"
|
||||
"+rA2LUK5IOQOgcUSTGKSqF9lYfAxPjrqPjDCUPHCURv+26ad5P/BYtXtbmtxJWu+\r\n"
|
||||
"cS5BhMDPPeG3oPZwXRHBJFAkY4O4AF7RIAAUW6EzDflUoDHKv83zOiPfYGcpHc9s\r\n"
|
||||
"kxAInCedk7QSgXvMARjjOqdakor21DTmNIUotxo8kHv5hwRlGhBJwps6fEVi1Bt0\r\n"
|
||||
"trpM/3wYxlr473WSPUFZPgP1j519kLpWOJ8z09wxay+Br29irPcBYv0GMXlHqThy\r\n"
|
||||
"8y4m/HyTQeI2IMvMrQnwqPpY+rLIXyviI2vLoI+4xKE4Rn38ZZ8m\r\n"
|
||||
"-----END CERTIFICATE-----\r\n";
|
||||
|
||||
const char *SPEECH_CERTIFICATE =
|
||||
"-----BEGIN CERTIFICATE-----\r\n"
|
||||
"MIIF8zCCBNugAwIBAgIQCq+mxcpjxFFB6jvh98dTFzANBgkqhkiG9w0BAQwFADBh\r\n"
|
||||
"MQswCQYDVQQGEwJVUzEVMBMGA1UEChMMRGlnaUNlcnQgSW5jMRkwFwYDVQQLExB3\r\n"
|
||||
"d3cuZGlnaWNlcnQuY29tMSAwHgYDVQQDExdEaWdpQ2VydCBHbG9iYWwgUm9vdCBH\r\n"
|
||||
"MjAeFw0yMDA3MjkxMjMwMDBaFw0yNDA2MjcyMzU5NTlaMFkxCzAJBgNVBAYTAlVT\r\n"
|
||||
"MR4wHAYDVQQKExVNaWNyb3NvZnQgQ29ycG9yYXRpb24xKjAoBgNVBAMTIU1pY3Jv\r\n"
|
||||
"c29mdCBBenVyZSBUTFMgSXNzdWluZyBDQSAwMTCCAiIwDQYJKoZIhvcNAQEBBQAD\r\n"
|
||||
"ggIPADCCAgoCggIBAMedcDrkXufP7pxVm1FHLDNA9IjwHaMoaY8arqqZ4Gff4xyr\r\n"
|
||||
"RygnavXL7g12MPAx8Q6Dd9hfBzrfWxkF0Br2wIvlvkzW01naNVSkHp+OS3hL3W6n\r\n"
|
||||
"l/jYvZnVeJXjtsKYcXIf/6WtspcF5awlQ9LZJcjwaH7KoZuK+THpXCMtzD8XNVdm\r\n"
|
||||
"GW/JI0C/7U/E7evXn9XDio8SYkGSM63aLO5BtLCv092+1d4GGBSQYolRq+7Pd1kR\r\n"
|
||||
"EkWBPm0ywZ2Vb8GIS5DLrjelEkBnKCyy3B0yQud9dpVsiUeE7F5sY8Me96WVxQcb\r\n"
|
||||
"OyYdEY/j/9UpDlOG+vA+YgOvBhkKEjiqygVpP8EZoMMijephzg43b5Qi9r5UrvYo\r\n"
|
||||
"o19oR/8pf4HJNDPF0/FJwFVMW8PmCBLGstin3NE1+NeWTkGt0TzpHjgKyfaDP2tO\r\n"
|
||||
"4bCk1G7pP2kDFT7SYfc8xbgCkFQ2UCEXsaH/f5YmpLn4YPiNFCeeIida7xnfTvc4\r\n"
|
||||
"7IxyVccHHq1FzGygOqemrxEETKh8hvDR6eBdrBwmCHVgZrnAqnn93JtGyPLi6+cj\r\n"
|
||||
"WGVGtMZHwzVvX1HvSFG771sskcEjJxiQNQDQRWHEh3NxvNb7kFlAXnVdRkkvhjpR\r\n"
|
||||
"GchFhTAzqmwltdWhWDEyCMKC2x/mSZvZtlZGY+g37Y72qHzidwtyW7rBetZJAgMB\r\n"
|
||||
"AAGjggGtMIIBqTAdBgNVHQ4EFgQUDyBd16FXlduSzyvQx8J3BM5ygHYwHwYDVR0j\r\n"
|
||||
"BBgwFoAUTiJUIBiV5uNu5g/6+rkS7QYXjzkwDgYDVR0PAQH/BAQDAgGGMB0GA1Ud\r\n"
|
||||
"JQQWMBQGCCsGAQUFBwMBBggrBgEFBQcDAjASBgNVHRMBAf8ECDAGAQH/AgEAMHYG\r\n"
|
||||
"CCsGAQUFBwEBBGowaDAkBggrBgEFBQcwAYYYaHR0cDovL29jc3AuZGlnaWNlcnQu\r\n"
|
||||
"Y29tMEAGCCsGAQUFBzAChjRodHRwOi8vY2FjZXJ0cy5kaWdpY2VydC5jb20vRGln\r\n"
|
||||
"aUNlcnRHbG9iYWxSb290RzIuY3J0MHsGA1UdHwR0MHIwN6A1oDOGMWh0dHA6Ly9j\r\n"
|
||||
"cmwzLmRpZ2ljZXJ0LmNvbS9EaWdpQ2VydEdsb2JhbFJvb3RHMi5jcmwwN6A1oDOG\r\n"
|
||||
"MWh0dHA6Ly9jcmw0LmRpZ2ljZXJ0LmNvbS9EaWdpQ2VydEdsb2JhbFJvb3RHMi5j\r\n"
|
||||
"cmwwHQYDVR0gBBYwFDAIBgZngQwBAgEwCAYGZ4EMAQICMBAGCSsGAQQBgjcVAQQD\r\n"
|
||||
"AgEAMA0GCSqGSIb3DQEBDAUAA4IBAQAlFvNh7QgXVLAZSsNR2XRmIn9iS8OHFCBA\r\n"
|
||||
"WxKJoi8YYQafpMTkMqeuzoL3HWb1pYEipsDkhiMnrpfeYZEA7Lz7yqEEtfgHcEBs\r\n"
|
||||
"K9KcStQGGZRfmWU07hPXHnFz+5gTXqzCE2PBMlRgVUYJiA25mJPXfB00gDvGhtYa\r\n"
|
||||
"+mENwM9Bq1B9YYLyLjRtUz8cyGsdyTIG/bBM/Q9jcV8JGqMU/UjAdh1pFyTnnHEl\r\n"
|
||||
"Y59Npi7F87ZqYYJEHJM2LGD+le8VsHjgeWX2CJQko7klXvcizuZvUEDTjHaQcs2J\r\n"
|
||||
"+kPgfyMIOY1DMJ21NxOJ2xPRC/wAh/hzSBRVtoAnyuxtkZ4VjIOh\r\n"
|
||||
"-----END CERTIFICATE-----\r\n";
|
@ -0,0 +1,69 @@
|
||||
#pragma once
|
||||
|
||||
#include <Arduino.h>
|
||||
#include <HTTPClient.h>
|
||||
#include <sfud.h>
|
||||
|
||||
#include "config.h"
|
||||
|
||||
class FlashStream : public Stream
|
||||
{
|
||||
public:
|
||||
FlashStream()
|
||||
{
|
||||
_pos = 0;
|
||||
_flash_address = 0;
|
||||
_flash = sfud_get_device_table() + 0;
|
||||
|
||||
populateBuffer();
|
||||
}
|
||||
|
||||
virtual size_t write(uint8_t val)
|
||||
{
|
||||
return 0;
|
||||
}
|
||||
|
||||
virtual int available()
|
||||
{
|
||||
int remaining = BUFFER_SIZE - ((_flash_address - HTTP_TCP_BUFFER_SIZE) + _pos);
|
||||
int bytes_available = min(HTTP_TCP_BUFFER_SIZE, remaining);
|
||||
|
||||
if (bytes_available == 0)
|
||||
{
|
||||
bytes_available = -1;
|
||||
}
|
||||
|
||||
return bytes_available;
|
||||
}
|
||||
|
||||
virtual int read()
|
||||
{
|
||||
int retVal = _buffer[_pos++];
|
||||
|
||||
if (_pos == HTTP_TCP_BUFFER_SIZE)
|
||||
{
|
||||
populateBuffer();
|
||||
}
|
||||
|
||||
return retVal;
|
||||
}
|
||||
|
||||
virtual int peek()
|
||||
{
|
||||
return _buffer[_pos];
|
||||
}
|
||||
|
||||
private:
|
||||
void populateBuffer()
|
||||
{
|
||||
sfud_read(_flash, _flash_address, HTTP_TCP_BUFFER_SIZE, _buffer);
|
||||
_flash_address += HTTP_TCP_BUFFER_SIZE;
|
||||
_pos = 0;
|
||||
}
|
||||
|
||||
size_t _pos;
|
||||
size_t _flash_address;
|
||||
const sfud_flash *_flash;
|
||||
|
||||
byte _buffer[HTTP_TCP_BUFFER_SIZE];
|
||||
};
|
@ -0,0 +1,60 @@
|
||||
#pragma once
|
||||
|
||||
#include <Arduino.h>
|
||||
#include <sfud.h>
|
||||
|
||||
class FlashWriter
|
||||
{
|
||||
public:
|
||||
void init()
|
||||
{
|
||||
_flash = sfud_get_device_table() + 0;
|
||||
_sfudBufferSize = _flash->chip.erase_gran;
|
||||
_sfudBuffer = new byte[_sfudBufferSize];
|
||||
_sfudBufferPos = 0;
|
||||
_sfudBufferWritePos = 0;
|
||||
}
|
||||
|
||||
void reset()
|
||||
{
|
||||
_sfudBufferPos = 0;
|
||||
_sfudBufferWritePos = 0;
|
||||
}
|
||||
|
||||
void writeSfudBuffer(byte b)
|
||||
{
|
||||
_sfudBuffer[_sfudBufferPos++] = b;
|
||||
if (_sfudBufferPos == _sfudBufferSize)
|
||||
{
|
||||
sfud_erase_write(_flash, _sfudBufferWritePos, _sfudBufferSize, _sfudBuffer);
|
||||
_sfudBufferWritePos += _sfudBufferSize;
|
||||
_sfudBufferPos = 0;
|
||||
}
|
||||
}
|
||||
|
||||
void flushSfudBuffer()
|
||||
{
|
||||
if (_sfudBufferPos > 0)
|
||||
{
|
||||
sfud_erase_write(_flash, _sfudBufferWritePos, _sfudBufferSize, _sfudBuffer);
|
||||
_sfudBufferWritePos += _sfudBufferSize;
|
||||
_sfudBufferPos = 0;
|
||||
}
|
||||
}
|
||||
|
||||
void writeSfudBuffer(byte *b, size_t len)
|
||||
{
|
||||
for (size_t i = 0; i < len; ++i)
|
||||
{
|
||||
writeSfudBuffer(b[i]);
|
||||
}
|
||||
}
|
||||
|
||||
private:
|
||||
byte *_sfudBuffer;
|
||||
size_t _sfudBufferSize;
|
||||
size_t _sfudBufferPos;
|
||||
size_t _sfudBufferWritePos;
|
||||
|
||||
const sfud_flash *_flash;
|
||||
};
|
@ -0,0 +1,53 @@
|
||||
#pragma once
|
||||
|
||||
#include <Arduino.h>
|
||||
#include <ArduinoJson.h>
|
||||
#include <HTTPClient.h>
|
||||
#include <WiFiClient.h>
|
||||
|
||||
#include "config.h"
|
||||
|
||||
class LanguageUnderstanding
|
||||
{
|
||||
public:
|
||||
int GetTimerDuration(String text)
|
||||
{
|
||||
DynamicJsonDocument doc(1024);
|
||||
doc["text"] = text;
|
||||
|
||||
String body;
|
||||
serializeJson(doc, body);
|
||||
|
||||
HTTPClient httpClient;
|
||||
httpClient.begin(_client, TEXT_TO_TIMER_FUNCTION_URL);
|
||||
|
||||
int httpResponseCode = httpClient.POST(body);
|
||||
|
||||
int seconds = 0;
|
||||
if (httpResponseCode == 200)
|
||||
{
|
||||
String result = httpClient.getString();
|
||||
Serial.println(result);
|
||||
|
||||
DynamicJsonDocument doc(1024);
|
||||
deserializeJson(doc, result.c_str());
|
||||
|
||||
JsonObject obj = doc.as<JsonObject>();
|
||||
seconds = obj["seconds"].as<int>();
|
||||
}
|
||||
else
|
||||
{
|
||||
Serial.print("Failed to understand text - error ");
|
||||
Serial.println(httpResponseCode);
|
||||
}
|
||||
|
||||
httpClient.end();
|
||||
|
||||
return seconds;
|
||||
}
|
||||
|
||||
private:
|
||||
WiFiClient _client;
|
||||
};
|
||||
|
||||
LanguageUnderstanding languageUnderstanding;
|
@ -0,0 +1,130 @@
|
||||
#include <Arduino.h>
|
||||
#include <arduino-timer.h>
|
||||
#include <rpcWiFi.h>
|
||||
#include <sfud.h>
|
||||
#include <SPI.h>
|
||||
|
||||
#include "config.h"
|
||||
#include "language_understanding.h"
|
||||
#include "mic.h"
|
||||
#include "speech_to_text.h"
|
||||
#include "text_to_speech.h"
|
||||
|
||||
void connectWiFi()
|
||||
{
|
||||
while (WiFi.status() != WL_CONNECTED)
|
||||
{
|
||||
Serial.println("Connecting to WiFi..");
|
||||
WiFi.begin(SSID, PASSWORD);
|
||||
delay(500);
|
||||
}
|
||||
|
||||
Serial.println("Connected!");
|
||||
}
|
||||
|
||||
void setup()
|
||||
{
|
||||
Serial.begin(9600);
|
||||
|
||||
while (!Serial)
|
||||
; // Wait for Serial to be ready
|
||||
|
||||
delay(1000);
|
||||
|
||||
connectWiFi();
|
||||
|
||||
while (!(sfud_init() == SFUD_SUCCESS))
|
||||
;
|
||||
|
||||
sfud_qspi_fast_read_enable(sfud_get_device(SFUD_W25Q32_DEVICE_INDEX), 2);
|
||||
|
||||
pinMode(WIO_KEY_C, INPUT_PULLUP);
|
||||
|
||||
mic.init();
|
||||
|
||||
speechToText.init();
|
||||
textToSpeech.init();
|
||||
|
||||
Serial.println("Ready.");
|
||||
}
|
||||
|
||||
auto timer = timer_create_default();
|
||||
|
||||
void say(String text)
|
||||
{
|
||||
Serial.println(text);
|
||||
textToSpeech.convertTextToSpeech(text);
|
||||
}
|
||||
|
||||
bool timerExpired(void *announcement)
|
||||
{
|
||||
say((char *)announcement);
|
||||
return false;
|
||||
}
|
||||
|
||||
void processAudio()
|
||||
{
|
||||
String text = speechToText.convertSpeechToText();
|
||||
Serial.println(text);
|
||||
|
||||
int total_seconds = languageUnderstanding.GetTimerDuration(text);
|
||||
if (total_seconds == 0)
|
||||
{
|
||||
return;
|
||||
}
|
||||
|
||||
int minutes = total_seconds / 60;
|
||||
int seconds = total_seconds % 60;
|
||||
|
||||
String begin_message;
|
||||
if (minutes > 0)
|
||||
{
|
||||
begin_message += minutes;
|
||||
begin_message += " minute ";
|
||||
}
|
||||
if (seconds > 0)
|
||||
{
|
||||
begin_message += seconds;
|
||||
begin_message += " second ";
|
||||
}
|
||||
|
||||
begin_message += "timer started.";
|
||||
|
||||
String end_message("Times up on your ");
|
||||
if (minutes > 0)
|
||||
{
|
||||
end_message += minutes;
|
||||
end_message += " minute ";
|
||||
}
|
||||
if (seconds > 0)
|
||||
{
|
||||
end_message += seconds;
|
||||
end_message += " second ";
|
||||
}
|
||||
|
||||
end_message += "timer.";
|
||||
|
||||
say(begin_message);
|
||||
|
||||
timer.in(total_seconds * 1000, timerExpired, (void *)(end_message.c_str()));
|
||||
}
|
||||
|
||||
void loop()
|
||||
{
|
||||
if (digitalRead(WIO_KEY_C) == LOW && !mic.isRecording())
|
||||
{
|
||||
Serial.println("Starting recording...");
|
||||
mic.startRecording();
|
||||
}
|
||||
|
||||
if (!mic.isRecording() && mic.isRecordingReady())
|
||||
{
|
||||
Serial.println("Finished recording");
|
||||
|
||||
processAudio();
|
||||
|
||||
mic.reset();
|
||||
}
|
||||
|
||||
timer.tick();
|
||||
}
|
@ -0,0 +1,242 @@
|
||||
#pragma once
|
||||
|
||||
#include <Arduino.h>
|
||||
|
||||
#include "config.h"
|
||||
#include "flash_writer.h"
|
||||
|
||||
class Mic
|
||||
{
|
||||
public:
|
||||
Mic()
|
||||
{
|
||||
_isRecording = false;
|
||||
_isRecordingReady = false;
|
||||
}
|
||||
|
||||
void startRecording()
|
||||
{
|
||||
_isRecording = true;
|
||||
_isRecordingReady = false;
|
||||
}
|
||||
|
||||
bool isRecording()
|
||||
{
|
||||
return _isRecording;
|
||||
}
|
||||
|
||||
bool isRecordingReady()
|
||||
{
|
||||
return _isRecordingReady;
|
||||
}
|
||||
|
||||
void init()
|
||||
{
|
||||
analogReference(AR_INTERNAL2V23);
|
||||
|
||||
_writer.init();
|
||||
|
||||
initBufferHeader();
|
||||
configureDmaAdc();
|
||||
}
|
||||
|
||||
void reset()
|
||||
{
|
||||
_isRecordingReady = false;
|
||||
_isRecording = false;
|
||||
|
||||
_writer.reset();
|
||||
|
||||
initBufferHeader();
|
||||
}
|
||||
|
||||
void dmaHandler()
|
||||
{
|
||||
static uint8_t count = 0;
|
||||
|
||||
if (DMAC->Channel[1].CHINTFLAG.bit.SUSP)
|
||||
{
|
||||
DMAC->Channel[1].CHCTRLB.reg = DMAC_CHCTRLB_CMD_RESUME;
|
||||
DMAC->Channel[1].CHINTFLAG.bit.SUSP = 1;
|
||||
|
||||
if (count)
|
||||
{
|
||||
audioCallback(_adc_buf_0, ADC_BUF_LEN);
|
||||
}
|
||||
else
|
||||
{
|
||||
audioCallback(_adc_buf_1, ADC_BUF_LEN);
|
||||
}
|
||||
|
||||
count = (count + 1) % 2;
|
||||
}
|
||||
}
|
||||
|
||||
private:
|
||||
volatile bool _isRecording;
|
||||
volatile bool _isRecordingReady;
|
||||
FlashWriter _writer;
|
||||
|
||||
typedef struct
|
||||
{
|
||||
uint16_t btctrl;
|
||||
uint16_t btcnt;
|
||||
uint32_t srcaddr;
|
||||
uint32_t dstaddr;
|
||||
uint32_t descaddr;
|
||||
} dmacdescriptor;
|
||||
|
||||
// Globals - DMA and ADC
|
||||
volatile dmacdescriptor _wrb[DMAC_CH_NUM] __attribute__((aligned(16)));
|
||||
dmacdescriptor _descriptor_section[DMAC_CH_NUM] __attribute__((aligned(16)));
|
||||
dmacdescriptor _descriptor __attribute__((aligned(16)));
|
||||
|
||||
void configureDmaAdc()
|
||||
{
|
||||
// Configure DMA to sample from ADC at a regular interval (triggered by timer/counter)
|
||||
DMAC->BASEADDR.reg = (uint32_t)_descriptor_section; // Specify the location of the descriptors
|
||||
DMAC->WRBADDR.reg = (uint32_t)_wrb; // Specify the location of the write back descriptors
|
||||
DMAC->CTRL.reg = DMAC_CTRL_DMAENABLE | DMAC_CTRL_LVLEN(0xf); // Enable the DMAC peripheral
|
||||
DMAC->Channel[1].CHCTRLA.reg = DMAC_CHCTRLA_TRIGSRC(TC5_DMAC_ID_OVF) | // Set DMAC to trigger on TC5 timer overflow
|
||||
DMAC_CHCTRLA_TRIGACT_BURST; // DMAC burst transfer
|
||||
|
||||
_descriptor.descaddr = (uint32_t)&_descriptor_section[1]; // Set up a circular descriptor
|
||||
_descriptor.srcaddr = (uint32_t)&ADC1->RESULT.reg; // Take the result from the ADC0 RESULT register
|
||||
_descriptor.dstaddr = (uint32_t)_adc_buf_0 + sizeof(uint16_t) * ADC_BUF_LEN; // Place it in the adc_buf_0 array
|
||||
_descriptor.btcnt = ADC_BUF_LEN; // Beat count
|
||||
_descriptor.btctrl = DMAC_BTCTRL_BEATSIZE_HWORD | // Beat size is HWORD (16-bits)
|
||||
DMAC_BTCTRL_DSTINC | // Increment the destination address
|
||||
DMAC_BTCTRL_VALID | // Descriptor is valid
|
||||
DMAC_BTCTRL_BLOCKACT_SUSPEND; // Suspend DMAC channel 0 after block transfer
|
||||
memcpy(&_descriptor_section[0], &_descriptor, sizeof(_descriptor)); // Copy the descriptor to the descriptor section
|
||||
|
||||
_descriptor.descaddr = (uint32_t)&_descriptor_section[0]; // Set up a circular descriptor
|
||||
_descriptor.srcaddr = (uint32_t)&ADC1->RESULT.reg; // Take the result from the ADC0 RESULT register
|
||||
_descriptor.dstaddr = (uint32_t)_adc_buf_1 + sizeof(uint16_t) * ADC_BUF_LEN; // Place it in the adc_buf_1 array
|
||||
_descriptor.btcnt = ADC_BUF_LEN; // Beat count
|
||||
_descriptor.btctrl = DMAC_BTCTRL_BEATSIZE_HWORD | // Beat size is HWORD (16-bits)
|
||||
DMAC_BTCTRL_DSTINC | // Increment the destination address
|
||||
DMAC_BTCTRL_VALID | // Descriptor is valid
|
||||
DMAC_BTCTRL_BLOCKACT_SUSPEND; // Suspend DMAC channel 0 after block transfer
|
||||
memcpy(&_descriptor_section[1], &_descriptor, sizeof(_descriptor)); // Copy the descriptor to the descriptor section
|
||||
|
||||
// Configure NVIC
|
||||
NVIC_SetPriority(DMAC_1_IRQn, 0); // Set the Nested Vector Interrupt Controller (NVIC) priority for DMAC1 to 0 (highest)
|
||||
NVIC_EnableIRQ(DMAC_1_IRQn); // Connect DMAC1 to Nested Vector Interrupt Controller (NVIC)
|
||||
|
||||
// Activate the suspend (SUSP) interrupt on DMAC channel 1
|
||||
DMAC->Channel[1].CHINTENSET.reg = DMAC_CHINTENSET_SUSP;
|
||||
|
||||
// Configure ADC
|
||||
ADC1->INPUTCTRL.bit.MUXPOS = ADC_INPUTCTRL_MUXPOS_AIN12_Val; // Set the analog input to ADC0/AIN2 (PB08 - A4 on Metro M4)
|
||||
while (ADC1->SYNCBUSY.bit.INPUTCTRL)
|
||||
; // Wait for synchronization
|
||||
ADC1->SAMPCTRL.bit.SAMPLEN = 0x00; // Set max Sampling Time Length to half divided ADC clock pulse (2.66us)
|
||||
while (ADC1->SYNCBUSY.bit.SAMPCTRL)
|
||||
; // Wait for synchronization
|
||||
ADC1->CTRLA.reg = ADC_CTRLA_PRESCALER_DIV128; // Divide Clock ADC GCLK by 128 (48MHz/128 = 375kHz)
|
||||
ADC1->CTRLB.reg = ADC_CTRLB_RESSEL_12BIT | // Set ADC resolution to 12 bits
|
||||
ADC_CTRLB_FREERUN; // Set ADC to free run mode
|
||||
while (ADC1->SYNCBUSY.bit.CTRLB)
|
||||
; // Wait for synchronization
|
||||
ADC1->CTRLA.bit.ENABLE = 1; // Enable the ADC
|
||||
while (ADC1->SYNCBUSY.bit.ENABLE)
|
||||
; // Wait for synchronization
|
||||
ADC1->SWTRIG.bit.START = 1; // Initiate a software trigger to start an ADC conversion
|
||||
while (ADC1->SYNCBUSY.bit.SWTRIG)
|
||||
; // Wait for synchronization
|
||||
|
||||
// Enable DMA channel 1
|
||||
DMAC->Channel[1].CHCTRLA.bit.ENABLE = 1;
|
||||
|
||||
// Configure Timer/Counter 5
|
||||
GCLK->PCHCTRL[TC5_GCLK_ID].reg = GCLK_PCHCTRL_CHEN | // Enable perhipheral channel for TC5
|
||||
GCLK_PCHCTRL_GEN_GCLK1; // Connect generic clock 0 at 48MHz
|
||||
|
||||
TC5->COUNT16.WAVE.reg = TC_WAVE_WAVEGEN_MFRQ; // Set TC5 to Match Frequency (MFRQ) mode
|
||||
TC5->COUNT16.CC[0].reg = 3000 - 1; // Set the trigger to 16 kHz: (4Mhz / 16000) - 1
|
||||
while (TC5->COUNT16.SYNCBUSY.bit.CC0)
|
||||
; // Wait for synchronization
|
||||
|
||||
// Start Timer/Counter 5
|
||||
TC5->COUNT16.CTRLA.bit.ENABLE = 1; // Enable the TC5 timer
|
||||
while (TC5->COUNT16.SYNCBUSY.bit.ENABLE)
|
||||
; // Wait for synchronization
|
||||
}
|
||||
|
||||
uint16_t _adc_buf_0[ADC_BUF_LEN];
|
||||
uint16_t _adc_buf_1[ADC_BUF_LEN];
|
||||
|
||||
// WAV files have a header. This struct defines that header
|
||||
struct wavFileHeader
|
||||
{
|
||||
char riff[4]; /* "RIFF" */
|
||||
long flength; /* file length in bytes */
|
||||
char wave[4]; /* "WAVE" */
|
||||
char fmt[4]; /* "fmt " */
|
||||
long chunk_size; /* size of FMT chunk in bytes (usually 16) */
|
||||
short format_tag; /* 1=PCM, 257=Mu-Law, 258=A-Law, 259=ADPCM */
|
||||
short num_chans; /* 1=mono, 2=stereo */
|
||||
long srate; /* Sampling rate in samples per second */
|
||||
long bytes_per_sec; /* bytes per second = srate*bytes_per_samp */
|
||||
short bytes_per_samp; /* 2=16-bit mono, 4=16-bit stereo */
|
||||
short bits_per_samp; /* Number of bits per sample */
|
||||
char data[4]; /* "data" */
|
||||
long dlength; /* data length in bytes (filelength - 44) */
|
||||
};
|
||||
|
||||
void initBufferHeader()
|
||||
{
|
||||
wavFileHeader wavh;
|
||||
|
||||
strncpy(wavh.riff, "RIFF", 4);
|
||||
strncpy(wavh.wave, "WAVE", 4);
|
||||
strncpy(wavh.fmt, "fmt ", 4);
|
||||
strncpy(wavh.data, "data", 4);
|
||||
|
||||
wavh.chunk_size = 16;
|
||||
wavh.format_tag = 1; // PCM
|
||||
wavh.num_chans = 1; // mono
|
||||
wavh.srate = RATE;
|
||||
wavh.bytes_per_sec = (RATE * 1 * 16 * 1) / 8;
|
||||
wavh.bytes_per_samp = 2;
|
||||
wavh.bits_per_samp = 16;
|
||||
wavh.dlength = RATE * 2 * 1 * 16 / 2;
|
||||
wavh.flength = wavh.dlength + 44;
|
||||
|
||||
_writer.writeSfudBuffer((byte *)&wavh, 44);
|
||||
}
|
||||
|
||||
void audioCallback(uint16_t *buf, uint32_t buf_len)
|
||||
{
|
||||
static uint32_t idx = 44;
|
||||
|
||||
if (_isRecording)
|
||||
{
|
||||
for (uint32_t i = 0; i < buf_len; i++)
|
||||
{
|
||||
int16_t audio_value = ((int16_t)buf[i] - 2048) * 16;
|
||||
|
||||
_writer.writeSfudBuffer(audio_value & 0xFF);
|
||||
_writer.writeSfudBuffer((audio_value >> 8) & 0xFF);
|
||||
}
|
||||
|
||||
idx += buf_len;
|
||||
|
||||
if (idx >= BUFFER_SIZE)
|
||||
{
|
||||
_writer.flushSfudBuffer();
|
||||
idx = 44;
|
||||
_isRecording = false;
|
||||
_isRecordingReady = true;
|
||||
}
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
Mic mic;
|
||||
|
||||
void DMAC_1_Handler()
|
||||
{
|
||||
mic.dmaHandler();
|
||||
}
|
@ -0,0 +1,102 @@
|
||||
#pragma once
|
||||
|
||||
#include <Arduino.h>
|
||||
#include <ArduinoJson.h>
|
||||
#include <HTTPClient.h>
|
||||
#include <WiFiClientSecure.h>
|
||||
|
||||
#include "config.h"
|
||||
#include "flash_stream.h"
|
||||
|
||||
class SpeechToText
|
||||
{
|
||||
public:
|
||||
void init()
|
||||
{
|
||||
_token_client.setCACert(TOKEN_CERTIFICATE);
|
||||
_speech_client.setCACert(SPEECH_CERTIFICATE);
|
||||
_access_token = getAccessToken();
|
||||
}
|
||||
|
||||
String convertSpeechToText()
|
||||
{
|
||||
char url[128];
|
||||
sprintf(url, SPEECH_URL, SPEECH_LOCATION, LANGUAGE);
|
||||
|
||||
HTTPClient httpClient;
|
||||
httpClient.begin(_speech_client, url);
|
||||
|
||||
httpClient.addHeader("Authorization", String("Bearer ") + _access_token);
|
||||
httpClient.addHeader("Content-Type", String("audio/wav; codecs=audio/pcm; samplerate=") + String(RATE));
|
||||
httpClient.addHeader("Accept", "application/json;text/xml");
|
||||
|
||||
Serial.println("Sending speech...");
|
||||
|
||||
FlashStream stream;
|
||||
int httpResponseCode = httpClient.sendRequest("POST", &stream, BUFFER_SIZE);
|
||||
|
||||
Serial.println("Speech sent!");
|
||||
|
||||
String text = "";
|
||||
|
||||
if (httpResponseCode == 200)
|
||||
{
|
||||
String result = httpClient.getString();
|
||||
Serial.println(result);
|
||||
|
||||
DynamicJsonDocument doc(1024);
|
||||
deserializeJson(doc, result.c_str());
|
||||
|
||||
JsonObject obj = doc.as<JsonObject>();
|
||||
text = obj["DisplayText"].as<String>();
|
||||
}
|
||||
else if (httpResponseCode == 401)
|
||||
{
|
||||
Serial.println("Access token expired, trying again with a new token");
|
||||
_access_token = getAccessToken();
|
||||
return convertSpeechToText();
|
||||
}
|
||||
else
|
||||
{
|
||||
Serial.print("Failed to convert text to speech - error ");
|
||||
Serial.println(httpResponseCode);
|
||||
}
|
||||
|
||||
httpClient.end();
|
||||
|
||||
return text;
|
||||
}
|
||||
|
||||
private:
|
||||
String getAccessToken()
|
||||
{
|
||||
char url[128];
|
||||
sprintf(url, TOKEN_URL, SPEECH_LOCATION);
|
||||
|
||||
HTTPClient httpClient;
|
||||
httpClient.begin(_token_client, url);
|
||||
|
||||
httpClient.addHeader("Ocp-Apim-Subscription-Key", SPEECH_API_KEY);
|
||||
int httpResultCode = httpClient.POST("{}");
|
||||
|
||||
if (httpResultCode != 200)
|
||||
{
|
||||
Serial.println("Error getting access token, trying again...");
|
||||
delay(10000);
|
||||
return getAccessToken();
|
||||
}
|
||||
|
||||
Serial.println("Got access token.");
|
||||
String result = httpClient.getString();
|
||||
|
||||
httpClient.end();
|
||||
|
||||
return result;
|
||||
}
|
||||
|
||||
WiFiClientSecure _token_client;
|
||||
WiFiClientSecure _speech_client;
|
||||
String _access_token;
|
||||
};
|
||||
|
||||
SpeechToText speechToText;
|
@ -0,0 +1,86 @@
|
||||
#pragma once
|
||||
|
||||
#include <Arduino.h>
|
||||
#include <ArduinoJson.h>
|
||||
#include <HTTPClient.h>
|
||||
#include <Seeed_FS.h>
|
||||
#include <SD/Seeed_SD.h>
|
||||
#include <WiFiClient.h>
|
||||
#include <WiFiClientSecure.h>
|
||||
|
||||
#include "config.h"
|
||||
|
||||
class TextToSpeech
|
||||
{
|
||||
public:
|
||||
void init()
|
||||
{
|
||||
DynamicJsonDocument doc(1024);
|
||||
doc["language"] = LANGUAGE;
|
||||
|
||||
String body;
|
||||
serializeJson(doc, body);
|
||||
|
||||
HTTPClient httpClient;
|
||||
httpClient.begin(_client, GET_VOICES_FUNCTION_URL);
|
||||
|
||||
int httpResponseCode = httpClient.POST(body);
|
||||
|
||||
if (httpResponseCode == 200)
|
||||
{
|
||||
String result = httpClient.getString();
|
||||
Serial.println(result);
|
||||
|
||||
DynamicJsonDocument doc(1024);
|
||||
deserializeJson(doc, result.c_str());
|
||||
|
||||
JsonArray obj = doc.as<JsonArray>();
|
||||
_voice = obj[0].as<String>();
|
||||
|
||||
Serial.print("Using voice ");
|
||||
Serial.println(_voice);
|
||||
}
|
||||
else
|
||||
{
|
||||
Serial.print("Failed to get voices - error ");
|
||||
Serial.println(httpResponseCode);
|
||||
}
|
||||
|
||||
httpClient.end();
|
||||
}
|
||||
|
||||
void convertTextToSpeech(String text)
|
||||
{
|
||||
DynamicJsonDocument doc(1024);
|
||||
doc["language"] = LANGUAGE;
|
||||
doc["voice"] = _voice;
|
||||
doc["text"] = text;
|
||||
|
||||
String body;
|
||||
serializeJson(doc, body);
|
||||
|
||||
HTTPClient httpClient;
|
||||
httpClient.begin(_client, TEXT_TO_SPEECH_FUNCTION_URL);
|
||||
|
||||
int httpResponseCode = httpClient.POST(body);
|
||||
|
||||
if (httpResponseCode == 200)
|
||||
{
|
||||
File wav_file = SD.open("SPEECH.WAV", FILE_WRITE);
|
||||
httpClient.writeToStream(&wav_file);
|
||||
wav_file.close();
|
||||
}
|
||||
else
|
||||
{
|
||||
Serial.print("Failed to get speech - error ");
|
||||
Serial.println(httpResponseCode);
|
||||
}
|
||||
|
||||
httpClient.end();
|
||||
}
|
||||
private:
|
||||
WiFiClient _client;
|
||||
String _voice;
|
||||
};
|
||||
|
||||
TextToSpeech textToSpeech;
|
@ -0,0 +1,11 @@
|
||||
|
||||
This directory is intended for PlatformIO Unit Testing and project tests.
|
||||
|
||||
Unit Testing is a software testing method by which individual units of
|
||||
source code, sets of one or more MCU program modules together with associated
|
||||
control data, usage procedures, and operating procedures, are tested to
|
||||
determine whether they are fit for use. Unit testing finds problems early
|
||||
in the development cycle.
|
||||
|
||||
More information about PlatformIO Unit Testing:
|
||||
- https://docs.platformio.org/page/plus/unit-testing.html
|
@ -0,0 +1,39 @@
|
||||
|
||||
This directory is intended for project header files.
|
||||
|
||||
A header file is a file containing C declarations and macro definitions
|
||||
to be shared between several project source files. You request the use of a
|
||||
header file in your project source file (C, C++, etc) located in `src` folder
|
||||
by including it, with the C preprocessing directive `#include'.
|
||||
|
||||
```src/main.c
|
||||
|
||||
#include "header.h"
|
||||
|
||||
int main (void)
|
||||
{
|
||||
...
|
||||
}
|
||||
```
|
||||
|
||||
Including a header file produces the same results as copying the header file
|
||||
into each source file that needs it. Such copying would be time-consuming
|
||||
and error-prone. With a header file, the related declarations appear
|
||||
in only one place. If they need to be changed, they can be changed in one
|
||||
place, and programs that include the header file will automatically use the
|
||||
new version when next recompiled. The header file eliminates the labor of
|
||||
finding and changing all the copies as well as the risk that a failure to
|
||||
find one copy will result in inconsistencies within a program.
|
||||
|
||||
In C, the usual convention is to give header files names that end with `.h'.
|
||||
It is most portable to use only letters, digits, dashes, and underscores in
|
||||
header file names, and at most one dot.
|
||||
|
||||
Read more about using header files in official GCC documentation:
|
||||
|
||||
* Include Syntax
|
||||
* Include Operation
|
||||
* Once-Only Headers
|
||||
* Computed Includes
|
||||
|
||||
https://gcc.gnu.org/onlinedocs/cpp/Header-Files.html
|
@ -0,0 +1,46 @@
|
||||
|
||||
This directory is intended for project specific (private) libraries.
|
||||
PlatformIO will compile them to static libraries and link into executable file.
|
||||
|
||||
The source code of each library should be placed in a an own separate directory
|
||||
("lib/your_library_name/[here are source files]").
|
||||
|
||||
For example, see a structure of the following two libraries `Foo` and `Bar`:
|
||||
|
||||
|--lib
|
||||
| |
|
||||
| |--Bar
|
||||
| | |--docs
|
||||
| | |--examples
|
||||
| | |--src
|
||||
| | |- Bar.c
|
||||
| | |- Bar.h
|
||||
| | |- library.json (optional, custom build options, etc) https://docs.platformio.org/page/librarymanager/config.html
|
||||
| |
|
||||
| |--Foo
|
||||
| | |- Foo.c
|
||||
| | |- Foo.h
|
||||
| |
|
||||
| |- README --> THIS FILE
|
||||
|
|
||||
|- platformio.ini
|
||||
|--src
|
||||
|- main.c
|
||||
|
||||
and a contents of `src/main.c`:
|
||||
```
|
||||
#include <Foo.h>
|
||||
#include <Bar.h>
|
||||
|
||||
int main (void)
|
||||
{
|
||||
...
|
||||
}
|
||||
|
||||
```
|
||||
|
||||
PlatformIO Library Dependency Finder will find automatically dependent
|
||||
libraries scanning project source files.
|
||||
|
||||
More information about PlatformIO Library Dependency Finder
|
||||
- https://docs.platformio.org/page/librarymanager/ldf.html
|
@ -0,0 +1,23 @@
|
||||
; PlatformIO Project Configuration File
|
||||
;
|
||||
; Build options: build flags, source filter
|
||||
; Upload options: custom upload port, speed and extra flags
|
||||
; Library options: dependencies, extra library storages
|
||||
; Advanced options: extra scripting
|
||||
;
|
||||
; Please visit documentation for the other options and examples
|
||||
; https://docs.platformio.org/page/projectconf.html
|
||||
|
||||
[env:seeed_wio_terminal]
|
||||
platform = atmelsam
|
||||
board = seeed_wio_terminal
|
||||
framework = arduino
|
||||
lib_deps =
|
||||
seeed-studio/Seeed Arduino FS @ 2.1.1
|
||||
seeed-studio/Seeed Arduino SFUD @ 2.0.2
|
||||
seeed-studio/Seeed Arduino rpcWiFi @ 1.0.5
|
||||
seeed-studio/Seeed Arduino rpcUnified @ 2.1.3
|
||||
seeed-studio/Seeed_Arduino_mbedtls @ 3.0.1
|
||||
seeed-studio/Seeed Arduino RTC @ 2.0.0
|
||||
bblanchon/ArduinoJson @ 6.17.3
|
||||
contrem/arduino-timer @ 2.3.0
|
@ -0,0 +1,91 @@
|
||||
#pragma once
|
||||
|
||||
#define RATE 16000
|
||||
#define SAMPLE_LENGTH_SECONDS 4
|
||||
#define SAMPLES RATE * SAMPLE_LENGTH_SECONDS
|
||||
#define BUFFER_SIZE (SAMPLES * 2) + 44
|
||||
#define ADC_BUF_LEN 1600
|
||||
|
||||
const char *SSID = "<SSID>";
|
||||
const char *PASSWORD = "<PASSWORD>";
|
||||
|
||||
const char *SPEECH_API_KEY = "<API_KEY>";
|
||||
const char *SPEECH_LOCATION = "<LOCATION>";
|
||||
const char *LANGUAGE = "<LANGUAGE>";
|
||||
|
||||
const char *TOKEN_URL = "https://%s.api.cognitive.microsoft.com/sts/v1.0/issuetoken";
|
||||
const char *SPEECH_URL = "https://%s.stt.speech.microsoft.com/speech/recognition/conversation/cognitiveservices/v1?language=%s";
|
||||
|
||||
const char *TEXT_TO_TIMER_FUNCTION_URL = "http://<IP_ADDRESS>:7071/api/text-to-timer";
|
||||
|
||||
const char *TOKEN_CERTIFICATE =
|
||||
"-----BEGIN CERTIFICATE-----\r\n"
|
||||
"MIIF8zCCBNugAwIBAgIQAueRcfuAIek/4tmDg0xQwDANBgkqhkiG9w0BAQwFADBh\r\n"
|
||||
"MQswCQYDVQQGEwJVUzEVMBMGA1UEChMMRGlnaUNlcnQgSW5jMRkwFwYDVQQLExB3\r\n"
|
||||
"d3cuZGlnaWNlcnQuY29tMSAwHgYDVQQDExdEaWdpQ2VydCBHbG9iYWwgUm9vdCBH\r\n"
|
||||
"MjAeFw0yMDA3MjkxMjMwMDBaFw0yNDA2MjcyMzU5NTlaMFkxCzAJBgNVBAYTAlVT\r\n"
|
||||
"MR4wHAYDVQQKExVNaWNyb3NvZnQgQ29ycG9yYXRpb24xKjAoBgNVBAMTIU1pY3Jv\r\n"
|
||||
"c29mdCBBenVyZSBUTFMgSXNzdWluZyBDQSAwNjCCAiIwDQYJKoZIhvcNAQEBBQAD\r\n"
|
||||
"ggIPADCCAgoCggIBALVGARl56bx3KBUSGuPc4H5uoNFkFH4e7pvTCxRi4j/+z+Xb\r\n"
|
||||
"wjEz+5CipDOqjx9/jWjskL5dk7PaQkzItidsAAnDCW1leZBOIi68Lff1bjTeZgMY\r\n"
|
||||
"iwdRd3Y39b/lcGpiuP2d23W95YHkMMT8IlWosYIX0f4kYb62rphyfnAjYb/4Od99\r\n"
|
||||
"ThnhlAxGtfvSbXcBVIKCYfZgqRvV+5lReUnd1aNjRYVzPOoifgSx2fRyy1+pO1Uz\r\n"
|
||||
"aMMNnIOE71bVYW0A1hr19w7kOb0KkJXoALTDDj1ukUEDqQuBfBxReL5mXiu1O7WG\r\n"
|
||||
"0vltg0VZ/SZzctBsdBlx1BkmWYBW261KZgBivrql5ELTKKd8qgtHcLQA5fl6JB0Q\r\n"
|
||||
"gs5XDaWehN86Gps5JW8ArjGtjcWAIP+X8CQaWfaCnuRm6Bk/03PQWhgdi84qwA0s\r\n"
|
||||
"sRfFJwHUPTNSnE8EiGVk2frt0u8PG1pwSQsFuNJfcYIHEv1vOzP7uEOuDydsmCjh\r\n"
|
||||
"lxuoK2n5/2aVR3BMTu+p4+gl8alXoBycyLmj3J/PUgqD8SL5fTCUegGsdia/Sa60\r\n"
|
||||
"N2oV7vQ17wjMN+LXa2rjj/b4ZlZgXVojDmAjDwIRdDUujQu0RVsJqFLMzSIHpp2C\r\n"
|
||||
"Zp7mIoLrySay2YYBu7SiNwL95X6He2kS8eefBBHjzwW/9FxGqry57i71c2cDAgMB\r\n"
|
||||
"AAGjggGtMIIBqTAdBgNVHQ4EFgQU1cFnOsKjnfR3UltZEjgp5lVou6UwHwYDVR0j\r\n"
|
||||
"BBgwFoAUTiJUIBiV5uNu5g/6+rkS7QYXjzkwDgYDVR0PAQH/BAQDAgGGMB0GA1Ud\r\n"
|
||||
"JQQWMBQGCCsGAQUFBwMBBggrBgEFBQcDAjASBgNVHRMBAf8ECDAGAQH/AgEAMHYG\r\n"
|
||||
"CCsGAQUFBwEBBGowaDAkBggrBgEFBQcwAYYYaHR0cDovL29jc3AuZGlnaWNlcnQu\r\n"
|
||||
"Y29tMEAGCCsGAQUFBzAChjRodHRwOi8vY2FjZXJ0cy5kaWdpY2VydC5jb20vRGln\r\n"
|
||||
"aUNlcnRHbG9iYWxSb290RzIuY3J0MHsGA1UdHwR0MHIwN6A1oDOGMWh0dHA6Ly9j\r\n"
|
||||
"cmwzLmRpZ2ljZXJ0LmNvbS9EaWdpQ2VydEdsb2JhbFJvb3RHMi5jcmwwN6A1oDOG\r\n"
|
||||
"MWh0dHA6Ly9jcmw0LmRpZ2ljZXJ0LmNvbS9EaWdpQ2VydEdsb2JhbFJvb3RHMi5j\r\n"
|
||||
"cmwwHQYDVR0gBBYwFDAIBgZngQwBAgEwCAYGZ4EMAQICMBAGCSsGAQQBgjcVAQQD\r\n"
|
||||
"AgEAMA0GCSqGSIb3DQEBDAUAA4IBAQB2oWc93fB8esci/8esixj++N22meiGDjgF\r\n"
|
||||
"+rA2LUK5IOQOgcUSTGKSqF9lYfAxPjrqPjDCUPHCURv+26ad5P/BYtXtbmtxJWu+\r\n"
|
||||
"cS5BhMDPPeG3oPZwXRHBJFAkY4O4AF7RIAAUW6EzDflUoDHKv83zOiPfYGcpHc9s\r\n"
|
||||
"kxAInCedk7QSgXvMARjjOqdakor21DTmNIUotxo8kHv5hwRlGhBJwps6fEVi1Bt0\r\n"
|
||||
"trpM/3wYxlr473WSPUFZPgP1j519kLpWOJ8z09wxay+Br29irPcBYv0GMXlHqThy\r\n"
|
||||
"8y4m/HyTQeI2IMvMrQnwqPpY+rLIXyviI2vLoI+4xKE4Rn38ZZ8m\r\n"
|
||||
"-----END CERTIFICATE-----\r\n";
|
||||
|
||||
const char *SPEECH_CERTIFICATE =
|
||||
"-----BEGIN CERTIFICATE-----\r\n"
|
||||
"MIIF8zCCBNugAwIBAgIQCq+mxcpjxFFB6jvh98dTFzANBgkqhkiG9w0BAQwFADBh\r\n"
|
||||
"MQswCQYDVQQGEwJVUzEVMBMGA1UEChMMRGlnaUNlcnQgSW5jMRkwFwYDVQQLExB3\r\n"
|
||||
"d3cuZGlnaWNlcnQuY29tMSAwHgYDVQQDExdEaWdpQ2VydCBHbG9iYWwgUm9vdCBH\r\n"
|
||||
"MjAeFw0yMDA3MjkxMjMwMDBaFw0yNDA2MjcyMzU5NTlaMFkxCzAJBgNVBAYTAlVT\r\n"
|
||||
"MR4wHAYDVQQKExVNaWNyb3NvZnQgQ29ycG9yYXRpb24xKjAoBgNVBAMTIU1pY3Jv\r\n"
|
||||
"c29mdCBBenVyZSBUTFMgSXNzdWluZyBDQSAwMTCCAiIwDQYJKoZIhvcNAQEBBQAD\r\n"
|
||||
"ggIPADCCAgoCggIBAMedcDrkXufP7pxVm1FHLDNA9IjwHaMoaY8arqqZ4Gff4xyr\r\n"
|
||||
"RygnavXL7g12MPAx8Q6Dd9hfBzrfWxkF0Br2wIvlvkzW01naNVSkHp+OS3hL3W6n\r\n"
|
||||
"l/jYvZnVeJXjtsKYcXIf/6WtspcF5awlQ9LZJcjwaH7KoZuK+THpXCMtzD8XNVdm\r\n"
|
||||
"GW/JI0C/7U/E7evXn9XDio8SYkGSM63aLO5BtLCv092+1d4GGBSQYolRq+7Pd1kR\r\n"
|
||||
"EkWBPm0ywZ2Vb8GIS5DLrjelEkBnKCyy3B0yQud9dpVsiUeE7F5sY8Me96WVxQcb\r\n"
|
||||
"OyYdEY/j/9UpDlOG+vA+YgOvBhkKEjiqygVpP8EZoMMijephzg43b5Qi9r5UrvYo\r\n"
|
||||
"o19oR/8pf4HJNDPF0/FJwFVMW8PmCBLGstin3NE1+NeWTkGt0TzpHjgKyfaDP2tO\r\n"
|
||||
"4bCk1G7pP2kDFT7SYfc8xbgCkFQ2UCEXsaH/f5YmpLn4YPiNFCeeIida7xnfTvc4\r\n"
|
||||
"7IxyVccHHq1FzGygOqemrxEETKh8hvDR6eBdrBwmCHVgZrnAqnn93JtGyPLi6+cj\r\n"
|
||||
"WGVGtMZHwzVvX1HvSFG771sskcEjJxiQNQDQRWHEh3NxvNb7kFlAXnVdRkkvhjpR\r\n"
|
||||
"GchFhTAzqmwltdWhWDEyCMKC2x/mSZvZtlZGY+g37Y72qHzidwtyW7rBetZJAgMB\r\n"
|
||||
"AAGjggGtMIIBqTAdBgNVHQ4EFgQUDyBd16FXlduSzyvQx8J3BM5ygHYwHwYDVR0j\r\n"
|
||||
"BBgwFoAUTiJUIBiV5uNu5g/6+rkS7QYXjzkwDgYDVR0PAQH/BAQDAgGGMB0GA1Ud\r\n"
|
||||
"JQQWMBQGCCsGAQUFBwMBBggrBgEFBQcDAjASBgNVHRMBAf8ECDAGAQH/AgEAMHYG\r\n"
|
||||
"CCsGAQUFBwEBBGowaDAkBggrBgEFBQcwAYYYaHR0cDovL29jc3AuZGlnaWNlcnQu\r\n"
|
||||
"Y29tMEAGCCsGAQUFBzAChjRodHRwOi8vY2FjZXJ0cy5kaWdpY2VydC5jb20vRGln\r\n"
|
||||
"aUNlcnRHbG9iYWxSb290RzIuY3J0MHsGA1UdHwR0MHIwN6A1oDOGMWh0dHA6Ly9j\r\n"
|
||||
"cmwzLmRpZ2ljZXJ0LmNvbS9EaWdpQ2VydEdsb2JhbFJvb3RHMi5jcmwwN6A1oDOG\r\n"
|
||||
"MWh0dHA6Ly9jcmw0LmRpZ2ljZXJ0LmNvbS9EaWdpQ2VydEdsb2JhbFJvb3RHMi5j\r\n"
|
||||
"cmwwHQYDVR0gBBYwFDAIBgZngQwBAgEwCAYGZ4EMAQICMBAGCSsGAQQBgjcVAQQD\r\n"
|
||||
"AgEAMA0GCSqGSIb3DQEBDAUAA4IBAQAlFvNh7QgXVLAZSsNR2XRmIn9iS8OHFCBA\r\n"
|
||||
"WxKJoi8YYQafpMTkMqeuzoL3HWb1pYEipsDkhiMnrpfeYZEA7Lz7yqEEtfgHcEBs\r\n"
|
||||
"K9KcStQGGZRfmWU07hPXHnFz+5gTXqzCE2PBMlRgVUYJiA25mJPXfB00gDvGhtYa\r\n"
|
||||
"+mENwM9Bq1B9YYLyLjRtUz8cyGsdyTIG/bBM/Q9jcV8JGqMU/UjAdh1pFyTnnHEl\r\n"
|
||||
"Y59Npi7F87ZqYYJEHJM2LGD+le8VsHjgeWX2CJQko7klXvcizuZvUEDTjHaQcs2J\r\n"
|
||||
"+kPgfyMIOY1DMJ21NxOJ2xPRC/wAh/hzSBRVtoAnyuxtkZ4VjIOh\r\n"
|
||||
"-----END CERTIFICATE-----\r\n";
|
@ -0,0 +1,69 @@
|
||||
#pragma once
|
||||
|
||||
#include <Arduino.h>
|
||||
#include <HTTPClient.h>
|
||||
#include <sfud.h>
|
||||
|
||||
#include "config.h"
|
||||
|
||||
class FlashStream : public Stream
|
||||
{
|
||||
public:
|
||||
FlashStream()
|
||||
{
|
||||
_pos = 0;
|
||||
_flash_address = 0;
|
||||
_flash = sfud_get_device_table() + 0;
|
||||
|
||||
populateBuffer();
|
||||
}
|
||||
|
||||
virtual size_t write(uint8_t val)
|
||||
{
|
||||
return 0;
|
||||
}
|
||||
|
||||
virtual int available()
|
||||
{
|
||||
int remaining = BUFFER_SIZE - ((_flash_address - HTTP_TCP_BUFFER_SIZE) + _pos);
|
||||
int bytes_available = min(HTTP_TCP_BUFFER_SIZE, remaining);
|
||||
|
||||
if (bytes_available == 0)
|
||||
{
|
||||
bytes_available = -1;
|
||||
}
|
||||
|
||||
return bytes_available;
|
||||
}
|
||||
|
||||
virtual int read()
|
||||
{
|
||||
int retVal = _buffer[_pos++];
|
||||
|
||||
if (_pos == HTTP_TCP_BUFFER_SIZE)
|
||||
{
|
||||
populateBuffer();
|
||||
}
|
||||
|
||||
return retVal;
|
||||
}
|
||||
|
||||
virtual int peek()
|
||||
{
|
||||
return _buffer[_pos];
|
||||
}
|
||||
|
||||
private:
|
||||
void populateBuffer()
|
||||
{
|
||||
sfud_read(_flash, _flash_address, HTTP_TCP_BUFFER_SIZE, _buffer);
|
||||
_flash_address += HTTP_TCP_BUFFER_SIZE;
|
||||
_pos = 0;
|
||||
}
|
||||
|
||||
size_t _pos;
|
||||
size_t _flash_address;
|
||||
const sfud_flash *_flash;
|
||||
|
||||
byte _buffer[HTTP_TCP_BUFFER_SIZE];
|
||||
};
|
@ -0,0 +1,60 @@
|
||||
#pragma once
|
||||
|
||||
#include <Arduino.h>
|
||||
#include <sfud.h>
|
||||
|
||||
class FlashWriter
|
||||
{
|
||||
public:
|
||||
void init()
|
||||
{
|
||||
_flash = sfud_get_device_table() + 0;
|
||||
_sfudBufferSize = _flash->chip.erase_gran;
|
||||
_sfudBuffer = new byte[_sfudBufferSize];
|
||||
_sfudBufferPos = 0;
|
||||
_sfudBufferWritePos = 0;
|
||||
}
|
||||
|
||||
void reset()
|
||||
{
|
||||
_sfudBufferPos = 0;
|
||||
_sfudBufferWritePos = 0;
|
||||
}
|
||||
|
||||
void writeSfudBuffer(byte b)
|
||||
{
|
||||
_sfudBuffer[_sfudBufferPos++] = b;
|
||||
if (_sfudBufferPos == _sfudBufferSize)
|
||||
{
|
||||
sfud_erase_write(_flash, _sfudBufferWritePos, _sfudBufferSize, _sfudBuffer);
|
||||
_sfudBufferWritePos += _sfudBufferSize;
|
||||
_sfudBufferPos = 0;
|
||||
}
|
||||
}
|
||||
|
||||
void flushSfudBuffer()
|
||||
{
|
||||
if (_sfudBufferPos > 0)
|
||||
{
|
||||
sfud_erase_write(_flash, _sfudBufferWritePos, _sfudBufferSize, _sfudBuffer);
|
||||
_sfudBufferWritePos += _sfudBufferSize;
|
||||
_sfudBufferPos = 0;
|
||||
}
|
||||
}
|
||||
|
||||
void writeSfudBuffer(byte *b, size_t len)
|
||||
{
|
||||
for (size_t i = 0; i < len; ++i)
|
||||
{
|
||||
writeSfudBuffer(b[i]);
|
||||
}
|
||||
}
|
||||
|
||||
private:
|
||||
byte *_sfudBuffer;
|
||||
size_t _sfudBufferSize;
|
||||
size_t _sfudBufferPos;
|
||||
size_t _sfudBufferWritePos;
|
||||
|
||||
const sfud_flash *_flash;
|
||||
};
|
@ -0,0 +1,53 @@
|
||||
#pragma once
|
||||
|
||||
#include <Arduino.h>
|
||||
#include <ArduinoJson.h>
|
||||
#include <HTTPClient.h>
|
||||
#include <WiFiClient.h>
|
||||
|
||||
#include "config.h"
|
||||
|
||||
class LanguageUnderstanding
|
||||
{
|
||||
public:
|
||||
int GetTimerDuration(String text)
|
||||
{
|
||||
DynamicJsonDocument doc(1024);
|
||||
doc["text"] = text;
|
||||
|
||||
String body;
|
||||
serializeJson(doc, body);
|
||||
|
||||
HTTPClient httpClient;
|
||||
httpClient.begin(_client, TEXT_TO_TIMER_FUNCTION_URL);
|
||||
|
||||
int httpResponseCode = httpClient.POST(body);
|
||||
|
||||
int seconds = 0;
|
||||
if (httpResponseCode == 200)
|
||||
{
|
||||
String result = httpClient.getString();
|
||||
Serial.println(result);
|
||||
|
||||
DynamicJsonDocument doc(1024);
|
||||
deserializeJson(doc, result.c_str());
|
||||
|
||||
JsonObject obj = doc.as<JsonObject>();
|
||||
seconds = obj["seconds"].as<int>();
|
||||
}
|
||||
else
|
||||
{
|
||||
Serial.print("Failed to understand text - error ");
|
||||
Serial.println(httpResponseCode);
|
||||
}
|
||||
|
||||
httpClient.end();
|
||||
|
||||
return seconds;
|
||||
}
|
||||
|
||||
private:
|
||||
WiFiClient _client;
|
||||
};
|
||||
|
||||
LanguageUnderstanding languageUnderstanding;
|
@ -0,0 +1,127 @@
|
||||
#include <Arduino.h>
|
||||
#include <arduino-timer.h>
|
||||
#include <rpcWiFi.h>
|
||||
#include <sfud.h>
|
||||
#include <SPI.h>
|
||||
|
||||
#include "config.h"
|
||||
#include "language_understanding.h"
|
||||
#include "mic.h"
|
||||
#include "speech_to_text.h"
|
||||
|
||||
void connectWiFi()
|
||||
{
|
||||
while (WiFi.status() != WL_CONNECTED)
|
||||
{
|
||||
Serial.println("Connecting to WiFi..");
|
||||
WiFi.begin(SSID, PASSWORD);
|
||||
delay(500);
|
||||
}
|
||||
|
||||
Serial.println("Connected!");
|
||||
}
|
||||
|
||||
void setup()
|
||||
{
|
||||
Serial.begin(9600);
|
||||
|
||||
while (!Serial)
|
||||
; // Wait for Serial to be ready
|
||||
|
||||
delay(1000);
|
||||
|
||||
connectWiFi();
|
||||
|
||||
while (!(sfud_init() == SFUD_SUCCESS))
|
||||
;
|
||||
|
||||
sfud_qspi_fast_read_enable(sfud_get_device(SFUD_W25Q32_DEVICE_INDEX), 2);
|
||||
|
||||
pinMode(WIO_KEY_C, INPUT_PULLUP);
|
||||
|
||||
mic.init();
|
||||
|
||||
speechToText.init();
|
||||
|
||||
Serial.println("Ready.");
|
||||
}
|
||||
|
||||
auto timer = timer_create_default();
|
||||
|
||||
void say(String text)
|
||||
{
|
||||
Serial.println(text);
|
||||
}
|
||||
|
||||
bool timerExpired(void *announcement)
|
||||
{
|
||||
say((char *)announcement);
|
||||
return false;
|
||||
}
|
||||
|
||||
void processAudio()
|
||||
{
|
||||
String text = speechToText.convertSpeechToText();
|
||||
Serial.println(text);
|
||||
|
||||
int total_seconds = languageUnderstanding.GetTimerDuration(text);
|
||||
if (total_seconds == 0)
|
||||
{
|
||||
return;
|
||||
}
|
||||
|
||||
int minutes = total_seconds / 60;
|
||||
int seconds = total_seconds % 60;
|
||||
|
||||
String begin_message;
|
||||
if (minutes > 0)
|
||||
{
|
||||
begin_message += minutes;
|
||||
begin_message += " minute ";
|
||||
}
|
||||
if (seconds > 0)
|
||||
{
|
||||
begin_message += seconds;
|
||||
begin_message += " second ";
|
||||
}
|
||||
|
||||
begin_message += "timer started.";
|
||||
|
||||
String end_message("Times up on your ");
|
||||
if (minutes > 0)
|
||||
{
|
||||
end_message += minutes;
|
||||
end_message += " minute ";
|
||||
}
|
||||
if (seconds > 0)
|
||||
{
|
||||
end_message += seconds;
|
||||
end_message += " second ";
|
||||
}
|
||||
|
||||
end_message += "timer.";
|
||||
|
||||
say(begin_message);
|
||||
|
||||
timer.in(total_seconds * 1000, timerExpired, (void *)(end_message.c_str()));
|
||||
}
|
||||
|
||||
void loop()
|
||||
{
|
||||
if (digitalRead(WIO_KEY_C) == LOW && !mic.isRecording())
|
||||
{
|
||||
Serial.println("Starting recording...");
|
||||
mic.startRecording();
|
||||
}
|
||||
|
||||
if (!mic.isRecording() && mic.isRecordingReady())
|
||||
{
|
||||
Serial.println("Finished recording");
|
||||
|
||||
processAudio();
|
||||
|
||||
mic.reset();
|
||||
}
|
||||
|
||||
timer.tick();
|
||||
}
|
@ -0,0 +1,242 @@
|
||||
#pragma once
|
||||
|
||||
#include <Arduino.h>
|
||||
|
||||
#include "config.h"
|
||||
#include "flash_writer.h"
|
||||
|
||||
class Mic
|
||||
{
|
||||
public:
|
||||
Mic()
|
||||
{
|
||||
_isRecording = false;
|
||||
_isRecordingReady = false;
|
||||
}
|
||||
|
||||
void startRecording()
|
||||
{
|
||||
_isRecording = true;
|
||||
_isRecordingReady = false;
|
||||
}
|
||||
|
||||
bool isRecording()
|
||||
{
|
||||
return _isRecording;
|
||||
}
|
||||
|
||||
bool isRecordingReady()
|
||||
{
|
||||
return _isRecordingReady;
|
||||
}
|
||||
|
||||
void init()
|
||||
{
|
||||
analogReference(AR_INTERNAL2V23);
|
||||
|
||||
_writer.init();
|
||||
|
||||
initBufferHeader();
|
||||
configureDmaAdc();
|
||||
}
|
||||
|
||||
void reset()
|
||||
{
|
||||
_isRecordingReady = false;
|
||||
_isRecording = false;
|
||||
|
||||
_writer.reset();
|
||||
|
||||
initBufferHeader();
|
||||
}
|
||||
|
||||
void dmaHandler()
|
||||
{
|
||||
static uint8_t count = 0;
|
||||
|
||||
if (DMAC->Channel[1].CHINTFLAG.bit.SUSP)
|
||||
{
|
||||
DMAC->Channel[1].CHCTRLB.reg = DMAC_CHCTRLB_CMD_RESUME;
|
||||
DMAC->Channel[1].CHINTFLAG.bit.SUSP = 1;
|
||||
|
||||
if (count)
|
||||
{
|
||||
audioCallback(_adc_buf_0, ADC_BUF_LEN);
|
||||
}
|
||||
else
|
||||
{
|
||||
audioCallback(_adc_buf_1, ADC_BUF_LEN);
|
||||
}
|
||||
|
||||
count = (count + 1) % 2;
|
||||
}
|
||||
}
|
||||
|
||||
private:
|
||||
volatile bool _isRecording;
|
||||
volatile bool _isRecordingReady;
|
||||
FlashWriter _writer;
|
||||
|
||||
typedef struct
|
||||
{
|
||||
uint16_t btctrl;
|
||||
uint16_t btcnt;
|
||||
uint32_t srcaddr;
|
||||
uint32_t dstaddr;
|
||||
uint32_t descaddr;
|
||||
} dmacdescriptor;
|
||||
|
||||
// Globals - DMA and ADC
|
||||
volatile dmacdescriptor _wrb[DMAC_CH_NUM] __attribute__((aligned(16)));
|
||||
dmacdescriptor _descriptor_section[DMAC_CH_NUM] __attribute__((aligned(16)));
|
||||
dmacdescriptor _descriptor __attribute__((aligned(16)));
|
||||
|
||||
void configureDmaAdc()
|
||||
{
|
||||
// Configure DMA to sample from ADC at a regular interval (triggered by timer/counter)
|
||||
DMAC->BASEADDR.reg = (uint32_t)_descriptor_section; // Specify the location of the descriptors
|
||||
DMAC->WRBADDR.reg = (uint32_t)_wrb; // Specify the location of the write back descriptors
|
||||
DMAC->CTRL.reg = DMAC_CTRL_DMAENABLE | DMAC_CTRL_LVLEN(0xf); // Enable the DMAC peripheral
|
||||
DMAC->Channel[1].CHCTRLA.reg = DMAC_CHCTRLA_TRIGSRC(TC5_DMAC_ID_OVF) | // Set DMAC to trigger on TC5 timer overflow
|
||||
DMAC_CHCTRLA_TRIGACT_BURST; // DMAC burst transfer
|
||||
|
||||
_descriptor.descaddr = (uint32_t)&_descriptor_section[1]; // Set up a circular descriptor
|
||||
_descriptor.srcaddr = (uint32_t)&ADC1->RESULT.reg; // Take the result from the ADC0 RESULT register
|
||||
_descriptor.dstaddr = (uint32_t)_adc_buf_0 + sizeof(uint16_t) * ADC_BUF_LEN; // Place it in the adc_buf_0 array
|
||||
_descriptor.btcnt = ADC_BUF_LEN; // Beat count
|
||||
_descriptor.btctrl = DMAC_BTCTRL_BEATSIZE_HWORD | // Beat size is HWORD (16-bits)
|
||||
DMAC_BTCTRL_DSTINC | // Increment the destination address
|
||||
DMAC_BTCTRL_VALID | // Descriptor is valid
|
||||
DMAC_BTCTRL_BLOCKACT_SUSPEND; // Suspend DMAC channel 0 after block transfer
|
||||
memcpy(&_descriptor_section[0], &_descriptor, sizeof(_descriptor)); // Copy the descriptor to the descriptor section
|
||||
|
||||
_descriptor.descaddr = (uint32_t)&_descriptor_section[0]; // Set up a circular descriptor
|
||||
_descriptor.srcaddr = (uint32_t)&ADC1->RESULT.reg; // Take the result from the ADC0 RESULT register
|
||||
_descriptor.dstaddr = (uint32_t)_adc_buf_1 + sizeof(uint16_t) * ADC_BUF_LEN; // Place it in the adc_buf_1 array
|
||||
_descriptor.btcnt = ADC_BUF_LEN; // Beat count
|
||||
_descriptor.btctrl = DMAC_BTCTRL_BEATSIZE_HWORD | // Beat size is HWORD (16-bits)
|
||||
DMAC_BTCTRL_DSTINC | // Increment the destination address
|
||||
DMAC_BTCTRL_VALID | // Descriptor is valid
|
||||
DMAC_BTCTRL_BLOCKACT_SUSPEND; // Suspend DMAC channel 0 after block transfer
|
||||
memcpy(&_descriptor_section[1], &_descriptor, sizeof(_descriptor)); // Copy the descriptor to the descriptor section
|
||||
|
||||
// Configure NVIC
|
||||
NVIC_SetPriority(DMAC_1_IRQn, 0); // Set the Nested Vector Interrupt Controller (NVIC) priority for DMAC1 to 0 (highest)
|
||||
NVIC_EnableIRQ(DMAC_1_IRQn); // Connect DMAC1 to Nested Vector Interrupt Controller (NVIC)
|
||||
|
||||
// Activate the suspend (SUSP) interrupt on DMAC channel 1
|
||||
DMAC->Channel[1].CHINTENSET.reg = DMAC_CHINTENSET_SUSP;
|
||||
|
||||
// Configure ADC
|
||||
ADC1->INPUTCTRL.bit.MUXPOS = ADC_INPUTCTRL_MUXPOS_AIN12_Val; // Set the analog input to ADC0/AIN2 (PB08 - A4 on Metro M4)
|
||||
while (ADC1->SYNCBUSY.bit.INPUTCTRL)
|
||||
; // Wait for synchronization
|
||||
ADC1->SAMPCTRL.bit.SAMPLEN = 0x00; // Set max Sampling Time Length to half divided ADC clock pulse (2.66us)
|
||||
while (ADC1->SYNCBUSY.bit.SAMPCTRL)
|
||||
; // Wait for synchronization
|
||||
ADC1->CTRLA.reg = ADC_CTRLA_PRESCALER_DIV128; // Divide Clock ADC GCLK by 128 (48MHz/128 = 375kHz)
|
||||
ADC1->CTRLB.reg = ADC_CTRLB_RESSEL_12BIT | // Set ADC resolution to 12 bits
|
||||
ADC_CTRLB_FREERUN; // Set ADC to free run mode
|
||||
while (ADC1->SYNCBUSY.bit.CTRLB)
|
||||
; // Wait for synchronization
|
||||
ADC1->CTRLA.bit.ENABLE = 1; // Enable the ADC
|
||||
while (ADC1->SYNCBUSY.bit.ENABLE)
|
||||
; // Wait for synchronization
|
||||
ADC1->SWTRIG.bit.START = 1; // Initiate a software trigger to start an ADC conversion
|
||||
while (ADC1->SYNCBUSY.bit.SWTRIG)
|
||||
; // Wait for synchronization
|
||||
|
||||
// Enable DMA channel 1
|
||||
DMAC->Channel[1].CHCTRLA.bit.ENABLE = 1;
|
||||
|
||||
// Configure Timer/Counter 5
|
||||
GCLK->PCHCTRL[TC5_GCLK_ID].reg = GCLK_PCHCTRL_CHEN | // Enable perhipheral channel for TC5
|
||||
GCLK_PCHCTRL_GEN_GCLK1; // Connect generic clock 0 at 48MHz
|
||||
|
||||
TC5->COUNT16.WAVE.reg = TC_WAVE_WAVEGEN_MFRQ; // Set TC5 to Match Frequency (MFRQ) mode
|
||||
TC5->COUNT16.CC[0].reg = 3000 - 1; // Set the trigger to 16 kHz: (4Mhz / 16000) - 1
|
||||
while (TC5->COUNT16.SYNCBUSY.bit.CC0)
|
||||
; // Wait for synchronization
|
||||
|
||||
// Start Timer/Counter 5
|
||||
TC5->COUNT16.CTRLA.bit.ENABLE = 1; // Enable the TC5 timer
|
||||
while (TC5->COUNT16.SYNCBUSY.bit.ENABLE)
|
||||
; // Wait for synchronization
|
||||
}
|
||||
|
||||
uint16_t _adc_buf_0[ADC_BUF_LEN];
|
||||
uint16_t _adc_buf_1[ADC_BUF_LEN];
|
||||
|
||||
// WAV files have a header. This struct defines that header
|
||||
struct wavFileHeader
|
||||
{
|
||||
char riff[4]; /* "RIFF" */
|
||||
long flength; /* file length in bytes */
|
||||
char wave[4]; /* "WAVE" */
|
||||
char fmt[4]; /* "fmt " */
|
||||
long chunk_size; /* size of FMT chunk in bytes (usually 16) */
|
||||
short format_tag; /* 1=PCM, 257=Mu-Law, 258=A-Law, 259=ADPCM */
|
||||
short num_chans; /* 1=mono, 2=stereo */
|
||||
long srate; /* Sampling rate in samples per second */
|
||||
long bytes_per_sec; /* bytes per second = srate*bytes_per_samp */
|
||||
short bytes_per_samp; /* 2=16-bit mono, 4=16-bit stereo */
|
||||
short bits_per_samp; /* Number of bits per sample */
|
||||
char data[4]; /* "data" */
|
||||
long dlength; /* data length in bytes (filelength - 44) */
|
||||
};
|
||||
|
||||
void initBufferHeader()
|
||||
{
|
||||
wavFileHeader wavh;
|
||||
|
||||
strncpy(wavh.riff, "RIFF", 4);
|
||||
strncpy(wavh.wave, "WAVE", 4);
|
||||
strncpy(wavh.fmt, "fmt ", 4);
|
||||
strncpy(wavh.data, "data", 4);
|
||||
|
||||
wavh.chunk_size = 16;
|
||||
wavh.format_tag = 1; // PCM
|
||||
wavh.num_chans = 1; // mono
|
||||
wavh.srate = RATE;
|
||||
wavh.bytes_per_sec = (RATE * 1 * 16 * 1) / 8;
|
||||
wavh.bytes_per_samp = 2;
|
||||
wavh.bits_per_samp = 16;
|
||||
wavh.dlength = RATE * 2 * 1 * 16 / 2;
|
||||
wavh.flength = wavh.dlength + 44;
|
||||
|
||||
_writer.writeSfudBuffer((byte *)&wavh, 44);
|
||||
}
|
||||
|
||||
void audioCallback(uint16_t *buf, uint32_t buf_len)
|
||||
{
|
||||
static uint32_t idx = 44;
|
||||
|
||||
if (_isRecording)
|
||||
{
|
||||
for (uint32_t i = 0; i < buf_len; i++)
|
||||
{
|
||||
int16_t audio_value = ((int16_t)buf[i] - 2048) * 16;
|
||||
|
||||
_writer.writeSfudBuffer(audio_value & 0xFF);
|
||||
_writer.writeSfudBuffer((audio_value >> 8) & 0xFF);
|
||||
}
|
||||
|
||||
idx += buf_len;
|
||||
|
||||
if (idx >= BUFFER_SIZE)
|
||||
{
|
||||
_writer.flushSfudBuffer();
|
||||
idx = 44;
|
||||
_isRecording = false;
|
||||
_isRecordingReady = true;
|
||||
}
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
Mic mic;
|
||||
|
||||
void DMAC_1_Handler()
|
||||
{
|
||||
mic.dmaHandler();
|
||||
}
|
@ -0,0 +1,102 @@
|
||||
#pragma once
|
||||
|
||||
#include <Arduino.h>
|
||||
#include <ArduinoJson.h>
|
||||
#include <HTTPClient.h>
|
||||
#include <WiFiClientSecure.h>
|
||||
|
||||
#include "config.h"
|
||||
#include "flash_stream.h"
|
||||
|
||||
class SpeechToText
|
||||
{
|
||||
public:
|
||||
void init()
|
||||
{
|
||||
_token_client.setCACert(TOKEN_CERTIFICATE);
|
||||
_speech_client.setCACert(SPEECH_CERTIFICATE);
|
||||
_access_token = getAccessToken();
|
||||
}
|
||||
|
||||
String convertSpeechToText()
|
||||
{
|
||||
char url[128];
|
||||
sprintf(url, SPEECH_URL, SPEECH_LOCATION, LANGUAGE);
|
||||
|
||||
HTTPClient httpClient;
|
||||
httpClient.begin(_speech_client, url);
|
||||
|
||||
httpClient.addHeader("Authorization", String("Bearer ") + _access_token);
|
||||
httpClient.addHeader("Content-Type", String("audio/wav; codecs=audio/pcm; samplerate=") + String(RATE));
|
||||
httpClient.addHeader("Accept", "application/json;text/xml");
|
||||
|
||||
Serial.println("Sending speech...");
|
||||
|
||||
FlashStream stream;
|
||||
int httpResponseCode = httpClient.sendRequest("POST", &stream, BUFFER_SIZE);
|
||||
|
||||
Serial.println("Speech sent!");
|
||||
|
||||
String text = "";
|
||||
|
||||
if (httpResponseCode == 200)
|
||||
{
|
||||
String result = httpClient.getString();
|
||||
Serial.println(result);
|
||||
|
||||
DynamicJsonDocument doc(1024);
|
||||
deserializeJson(doc, result.c_str());
|
||||
|
||||
JsonObject obj = doc.as<JsonObject>();
|
||||
text = obj["DisplayText"].as<String>();
|
||||
}
|
||||
else if (httpResponseCode == 401)
|
||||
{
|
||||
Serial.println("Access token expired, trying again with a new token");
|
||||
_access_token = getAccessToken();
|
||||
return convertSpeechToText();
|
||||
}
|
||||
else
|
||||
{
|
||||
Serial.print("Failed to convert text to speech - error ");
|
||||
Serial.println(httpResponseCode);
|
||||
}
|
||||
|
||||
httpClient.end();
|
||||
|
||||
return text;
|
||||
}
|
||||
|
||||
private:
|
||||
String getAccessToken()
|
||||
{
|
||||
char url[128];
|
||||
sprintf(url, TOKEN_URL, SPEECH_LOCATION);
|
||||
|
||||
HTTPClient httpClient;
|
||||
httpClient.begin(_token_client, url);
|
||||
|
||||
httpClient.addHeader("Ocp-Apim-Subscription-Key", SPEECH_API_KEY);
|
||||
int httpResultCode = httpClient.POST("{}");
|
||||
|
||||
if (httpResultCode != 200)
|
||||
{
|
||||
Serial.println("Error getting access token, trying again...");
|
||||
delay(10000);
|
||||
return getAccessToken();
|
||||
}
|
||||
|
||||
Serial.println("Got access token.");
|
||||
String result = httpClient.getString();
|
||||
|
||||
httpClient.end();
|
||||
|
||||
return result;
|
||||
}
|
||||
|
||||
WiFiClientSecure _token_client;
|
||||
WiFiClientSecure _speech_client;
|
||||
String _access_token;
|
||||
};
|
||||
|
||||
SpeechToText speechToText;
|
@ -0,0 +1,11 @@
|
||||
|
||||
This directory is intended for PlatformIO Unit Testing and project tests.
|
||||
|
||||
Unit Testing is a software testing method by which individual units of
|
||||
source code, sets of one or more MCU program modules together with associated
|
||||
control data, usage procedures, and operating procedures, are tested to
|
||||
determine whether they are fit for use. Unit testing finds problems early
|
||||
in the development cycle.
|
||||
|
||||
More information about PlatformIO Unit Testing:
|
||||
- https://docs.platformio.org/page/plus/unit-testing.html
|
@ -1,3 +1,287 @@
|
||||
# Set a timer - Wio Terminal
|
||||
|
||||
Coming soon
|
||||
In this part of the lesson, you will call your serverless code to understand the speech, and set a timer on your Wio Terminal based off the results.
|
||||
|
||||
## Set a timer
|
||||
|
||||
The text that comes back from the speech to text call needs to be sent to your serverless code to be processed by LUIS, getting back the number of seconds for the timer. This number of seconds can be used to set a timer.
|
||||
|
||||
Microcontrollers don't natively have support for multiple threads in Arduino, so there are no standard timer classes like you might find when coding in Python or other higher-level languages. Instead you can use timer libraries that work by measuring elapsed time in the `loop` function, and calling functions when the time is up.
|
||||
|
||||
### Task - send the text to the serverless function
|
||||
|
||||
1. Open the `smart-timer` project in VS Code if it is not already open.
|
||||
|
||||
1. Open the `config.h` header file and add the URL for your function app:
|
||||
|
||||
```cpp
|
||||
const char *TEXT_TO_TIMER_FUNCTION_URL = "<URL>";
|
||||
```
|
||||
|
||||
Replace `<URL>` with the URL for your function app that you obtained in the last step of the last lesson, pointing to the IP address of your local machine that is running the function app.
|
||||
|
||||
1. Create a new file in the `src` folder called `language_understanding.h`. This will be used to define a class to send the recognized speech to your function app to be converted to seconds using LUIS.
|
||||
|
||||
1. Add the following to the top of this file:
|
||||
|
||||
```cpp
|
||||
#pragma once
|
||||
|
||||
#include <Arduino.h>
|
||||
#include <ArduinoJson.h>
|
||||
#include <HTTPClient.h>
|
||||
#include <WiFiClient.h>
|
||||
|
||||
#include "config.h"
|
||||
```
|
||||
|
||||
This includes some needed header files.
|
||||
|
||||
1. Define a class called `LanguageUnderstanding`, and declare an instance of this class:
|
||||
|
||||
```cpp
|
||||
class LanguageUnderstanding
|
||||
{
|
||||
public:
|
||||
private:
|
||||
};
|
||||
|
||||
LanguageUnderstanding languageUnderstanding;
|
||||
```
|
||||
|
||||
1. To call your functions app, you need to declare a WiFi client. Add the following to the `private` section of the class:
|
||||
|
||||
```cpp
|
||||
WiFiClient _client;
|
||||
```
|
||||
|
||||
1. In the `public` section, declare a method called `GetTimerDuration` to call the functions app:
|
||||
|
||||
```cpp
|
||||
int GetTimerDuration(String text)
|
||||
{
|
||||
}
|
||||
```
|
||||
|
||||
1. In the `GetTimerDuration` method, add the following code to build the JSON to be sent to the functions app:
|
||||
|
||||
```cpp
|
||||
DynamicJsonDocument doc(1024);
|
||||
doc["text"] = text;
|
||||
|
||||
String body;
|
||||
serializeJson(doc, body);
|
||||
```
|
||||
|
||||
This coverts the text passed to the `GetTimerDuration` method into the following JSON:
|
||||
|
||||
```json
|
||||
{
|
||||
"text" : "<text>"
|
||||
}
|
||||
```
|
||||
|
||||
where `<text>` is the text passed to the function.
|
||||
|
||||
1. Below this, add the following code to make the functions app call:
|
||||
|
||||
```cpp
|
||||
HTTPClient httpClient;
|
||||
httpClient.begin(_client, TEXT_TO_TIMER_FUNCTION_URL);
|
||||
|
||||
int httpResponseCode = httpClient.POST(body);
|
||||
```
|
||||
|
||||
This makes a POST request to the functions app, passing the JSON body and getting the response code.
|
||||
|
||||
1. Add the following code below this:
|
||||
|
||||
```cpp
|
||||
int seconds = 0;
|
||||
if (httpResponseCode == 200)
|
||||
{
|
||||
String result = httpClient.getString();
|
||||
Serial.println(result);
|
||||
|
||||
DynamicJsonDocument doc(1024);
|
||||
deserializeJson(doc, result.c_str());
|
||||
|
||||
JsonObject obj = doc.as<JsonObject>();
|
||||
seconds = obj["seconds"].as<int>();
|
||||
}
|
||||
else
|
||||
{
|
||||
Serial.print("Failed to understand text - error ");
|
||||
Serial.println(httpResponseCode);
|
||||
}
|
||||
```
|
||||
|
||||
This code checks the response code. If it is 200 (success), then the number of seconds for the time is retrieved from the response body. Otherwise an error is sent to the serial monitor and the number of seconds is set to 0.
|
||||
|
||||
1. Add the following code to the end of this method to close the HTTP connection and return the number of seconds:
|
||||
|
||||
```cpp
|
||||
httpClient.end();
|
||||
|
||||
return seconds;
|
||||
```
|
||||
|
||||
1. In the `main.cpp` file, include this new header:
|
||||
|
||||
```cpp
|
||||
#include "speech_to_text.h"
|
||||
```
|
||||
|
||||
1. On the end of the `processAudio` function, call the `GetTimerDuration` method to get the timer duration:
|
||||
|
||||
```cpp
|
||||
int total_seconds = languageUnderstanding.GetTimerDuration(text);
|
||||
```
|
||||
|
||||
This converts the text from the call to the `SpeechToText` class into the number of seconds for the timer.
|
||||
|
||||
### Task - set a timer
|
||||
|
||||
The number of seconds can be used to set a timer.
|
||||
|
||||
1. Add the following library dependency to the `platformio.ini` file to add a library to set a timer:
|
||||
|
||||
```ini
|
||||
contrem/arduino-timer @ 2.3.0
|
||||
```
|
||||
|
||||
1. Add an include directive for this library to the `main.cpp` file:
|
||||
|
||||
```cpp
|
||||
#include <arduino-timer.h>
|
||||
```
|
||||
|
||||
1. Above the `processAudio` function, add the following code:
|
||||
|
||||
```cpp
|
||||
auto timer = timer_create_default();
|
||||
```
|
||||
|
||||
This code declares a timer called `timer`.
|
||||
|
||||
1. Below this, add the following code:
|
||||
|
||||
```cpp
|
||||
void say(String text)
|
||||
{
|
||||
Serial.print("Saying ");
|
||||
Serial.println(text);
|
||||
}
|
||||
```
|
||||
|
||||
This `say` function will eventually convert text to speech, but for now it will just write the passed in text to the serial monitor.
|
||||
|
||||
1. Below the `say` function, add the following code:
|
||||
|
||||
```cpp
|
||||
bool timerExpired(void *announcement)
|
||||
{
|
||||
say((char *)announcement);
|
||||
return false;
|
||||
}
|
||||
```
|
||||
|
||||
This is a callback function that will be called when a timer expires. It is passed a message to say when the timer expires. Timers can repeat, and this can be controlled by the return value of this callback - this returns `false`, to tell the timer to not run again.
|
||||
|
||||
1. Add the following code to the end of the `processAudio` function:
|
||||
|
||||
```cpp
|
||||
if (total_seconds == 0)
|
||||
{
|
||||
return;
|
||||
}
|
||||
|
||||
int minutes = total_seconds / 60;
|
||||
int seconds = total_seconds % 60;
|
||||
```
|
||||
|
||||
This code checks the total number of seconds, and if it is 0, returns from teh function call so no timers are set. It then converts the total number of seconds into minutes and seconds.
|
||||
|
||||
1. Below this code, add the following to create a message to say when the timer is started:
|
||||
|
||||
```cpp
|
||||
String begin_message;
|
||||
if (minutes > 0)
|
||||
{
|
||||
begin_message += minutes;
|
||||
begin_message += " minute ";
|
||||
}
|
||||
if (seconds > 0)
|
||||
{
|
||||
begin_message += seconds;
|
||||
begin_message += " second ";
|
||||
}
|
||||
|
||||
begin_message += "timer started.";
|
||||
```
|
||||
|
||||
1. Below this, add similar code to create a message to say when the timer has expired:
|
||||
|
||||
```cpp
|
||||
String end_message("Times up on your ");
|
||||
if (minutes > 0)
|
||||
{
|
||||
end_message += minutes;
|
||||
end_message += " minute ";
|
||||
}
|
||||
if (seconds > 0)
|
||||
{
|
||||
end_message += seconds;
|
||||
end_message += " second ";
|
||||
}
|
||||
|
||||
end_message += "timer.";
|
||||
```
|
||||
|
||||
1. After this, say the timer started message:
|
||||
|
||||
```cpp
|
||||
say(begin_message);
|
||||
```
|
||||
|
||||
1. At the end of this function, start the timer:
|
||||
|
||||
```cpp
|
||||
timer.in(total_seconds * 1000, timerExpired, (void *)(end_message.c_str()));
|
||||
```
|
||||
|
||||
This triggers the timer. The timer is set using milliseconds, so the total number of seconds is multiplied by 1,000 to convert to milliseconds. The `timerExpired` function is passed as the callback, and the `end_message` is passed as an argument to pass to the callback. This callback only takes `void *` arguments, so the string is converted appropriately.
|
||||
|
||||
1. Finally, the timer needs to *tick*, and this is done in the `loop` function. Add the following code at the end of the `loop` function:
|
||||
|
||||
```cpp
|
||||
timer.tick();
|
||||
```
|
||||
|
||||
1. Build this code, upload it to your Wio Terminal and test it out through the serial monitor. Once you see `Ready` in the serial monitor, press the C button (the one on the left-hand side, closest to the power switch), and speak. 4 seconds of audio will be captured, converted to text, then sent to your function app, and a timer will be set. Make sure your functions app is running locally.
|
||||
|
||||
You will see when the timer starts, and when it ends.
|
||||
|
||||
```output
|
||||
--- Available filters and text transformations: colorize, debug, default, direct, hexlify, log2file, nocontrol, printable, send_on_enter, time
|
||||
--- More details at http://bit.ly/pio-monitor-filters
|
||||
--- Miniterm on /dev/cu.usbmodem1101 9600,8,N,1 ---
|
||||
--- Quit: Ctrl+C | Menu: Ctrl+T | Help: Ctrl+T followed by Ctrl+H ---
|
||||
Connecting to WiFi..
|
||||
Connected!
|
||||
Got access token.
|
||||
Ready.
|
||||
Starting recording...
|
||||
Finished recording
|
||||
Sending speech...
|
||||
Speech sent!
|
||||
{"RecognitionStatus":"Success","DisplayText":"Set a 2 minute and 27 second timer.","Offset":4700000,"Duration":35300000}
|
||||
Set a 2 minute and 27 second timer.
|
||||
{"seconds": 147}
|
||||
2 minute 27 second timer started.
|
||||
Times up on your 2 minute 27 second timer.
|
||||
```
|
||||
|
||||
> 💁 You can find this code in the [code-timer/wio-terminal](code-timer/wio-terminal) folder.
|
||||
|
||||
😀 Your timer program was a success!
|
||||
|
@ -1,3 +1,522 @@
|
||||
# Text to speech - Wio Terminal
|
||||
|
||||
Coming soon
|
||||
In this part of the lesson, you will convert text to speech to provide spoken feedback.
|
||||
|
||||
## Text to speech
|
||||
|
||||
The speech services SDK that you used in the last lesson to convert speech to text can be used to convert text back to speech.
|
||||
|
||||
## Get a list of voices
|
||||
|
||||
When requesting speech, you need to provide the voice to use as speech can be generated using a variety of different voices. Each language supports a range of different voices, and you can get the list of supported voices for each language from the speech services SDK. The limitations of microcontrollers come into play here - the call to get the list of voices supported by the text to speech services is a JSON document of over 77KB in size, far to large to be processed by the Wio Terminal. At the time of writing, the full list contains 215 voices, each defined by a JSON document like the following:
|
||||
|
||||
```json
|
||||
{
|
||||
"Name": "Microsoft Server Speech Text to Speech Voice (en-US, AriaNeural)",
|
||||
"DisplayName": "Aria",
|
||||
"LocalName": "Aria",
|
||||
"ShortName": "en-US-AriaNeural",
|
||||
"Gender": "Female",
|
||||
"Locale": "en-US",
|
||||
"StyleList": [
|
||||
"chat",
|
||||
"customerservice",
|
||||
"narration-professional",
|
||||
"newscast-casual",
|
||||
"newscast-formal",
|
||||
"cheerful",
|
||||
"empathetic"
|
||||
],
|
||||
"SampleRateHertz": "24000",
|
||||
"VoiceType": "Neural",
|
||||
"Status": "GA"
|
||||
}
|
||||
```
|
||||
|
||||
This JSON is for the **Aria** voice, which has multiple voice styles. All that is needed when converting text to speech is the shortname, `en-US-AriaNeural`.
|
||||
|
||||
Instead of downloading and decoding this entire list on your microcontroller, you will need to write some more serverless code to retrieve the list of voices for the language you are using, and call this from your Wio Terminal. Your code can then pick an appropriate voice from the list, such as the first one it finds.
|
||||
|
||||
### Task - create a serverless function to get a list of voices
|
||||
|
||||
1. Open your `smart-timer-trigger` project in VS Code, and open the terminal ensuring the virtual environment is activated. If not, kill and re-create the terminal.
|
||||
|
||||
1. Open the `local.settings.json` file and add settings for the speech API key and location:
|
||||
|
||||
```json
|
||||
"SPEECH_KEY": "<key>",
|
||||
"SPEECH_LOCATION": "<location>"
|
||||
```
|
||||
|
||||
Replace `<key>` with the API key for your speech service resource. Replace `<location>` with the location you used when you created the speech service resource.
|
||||
|
||||
1. Add a new HTTP trigger to this app called `get-voices` using the following command from inside the VS Code terminal in the root folder of the functions app project:
|
||||
|
||||
```sh
|
||||
func new --name get-voices --template "HTTP trigger"
|
||||
```
|
||||
|
||||
This will create an HTTP trigger called `get-voices`.
|
||||
|
||||
1. Replace the contents of the `__init__.py` file in the `get-voices` folder with the following:
|
||||
|
||||
```python
|
||||
import json
|
||||
import os
|
||||
import requests
|
||||
|
||||
import azure.functions as func
|
||||
|
||||
def main(req: func.HttpRequest) -> func.HttpResponse:
|
||||
location = os.environ['SPEECH_LOCATION']
|
||||
speech_key = os.environ['SPEECH_KEY']
|
||||
|
||||
req_body = req.get_json()
|
||||
language = req_body['language']
|
||||
|
||||
url = f'https://{location}.tts.speech.microsoft.com/cognitiveservices/voices/list'
|
||||
|
||||
headers = {
|
||||
'Ocp-Apim-Subscription-Key': speech_key
|
||||
}
|
||||
|
||||
response = requests.get(url, headers=headers)
|
||||
voices_json = json.loads(response.text)
|
||||
|
||||
voices = filter(lambda x: x['Locale'].lower() == language.lower(), voices_json)
|
||||
voices = map(lambda x: x['ShortName'], voices)
|
||||
|
||||
return func.HttpResponse(json.dumps(list(voices)), status_code=200)
|
||||
```
|
||||
|
||||
This code makes an HTTP request to the endpoint to get the voices. This voices list is a large block of JSON with voices for all languages, so the voices for the language passed in the request body are filtered out, then the shortname is extracted and returned as a JSON list. The shortname is the value needed to convert text to speech, so only this value is returned.
|
||||
|
||||
> 💁 You can change the filter as necessary to select just the voices you want.
|
||||
|
||||
This reduces the size of the data from 77KB (at the time of writing), to a much smaller JSON document. For example, for US voices this is 408 bytes.
|
||||
|
||||
1. Run your function app locally. You can then call this using a tool like curl in the same way that you tested your `text-to-timer` HTTP trigger. Make sure to pass your language as a JSON body:
|
||||
|
||||
```json
|
||||
{
|
||||
"language":"<language>"
|
||||
}
|
||||
```
|
||||
|
||||
Replace `<language>` with your language, such as `en-GB`, or `zh-CN`.
|
||||
|
||||
> 💁 You can find this code in the [code-spoken-response/functions](code-spoken-response/functions) folder.
|
||||
|
||||
### Task - retrieve the voice from your Wio Terminal
|
||||
|
||||
1. Open the `smart-timer` project in VS Code if it is not already open.
|
||||
|
||||
1. Open the `config.h` header file and add the URL for your function app:
|
||||
|
||||
```cpp
|
||||
const char *GET_VOICES_FUNCTION_URL = "<URL>";
|
||||
```
|
||||
|
||||
Replace `<URL>` with the URL for the `get-voices` HTTP trigger on your function app. This will be the same as the value for `TEXT_TO_TIMER_FUNCTION_URL`, except with a function name of `get-voices` instead of `text-to-timer`.
|
||||
|
||||
1. Create a new file in the `src` folder called `text_to_speech.h`. This will be used to define a class to convert from text to speech.
|
||||
|
||||
1. Add the following include directives to the top of the new `text_to_speech.h` file:
|
||||
|
||||
```cpp
|
||||
#pragma once
|
||||
|
||||
#include <Arduino.h>
|
||||
#include <ArduinoJson.h>
|
||||
#include <HTTPClient.h>
|
||||
#include <Seeed_FS.h>
|
||||
#include <SD/Seeed_SD.h>
|
||||
#include <WiFiClient.h>
|
||||
#include <WiFiClientSecure.h>
|
||||
|
||||
#include "config.h"
|
||||
#include "speech_to_text.h"
|
||||
```
|
||||
|
||||
1. Add the following code below this to declare the `TextToSpeech` class, along with an instance that can be used in the rest of the application:
|
||||
|
||||
```cpp
|
||||
class TextToSpeech
|
||||
{
|
||||
public:
|
||||
private:
|
||||
};
|
||||
|
||||
TextToSpeech textToSpeech;
|
||||
```
|
||||
|
||||
1. To call your functions app, you need to declare a WiFi client. Add the following to the `private` section of the class:
|
||||
|
||||
```cpp
|
||||
WiFiClient _client;
|
||||
```
|
||||
|
||||
1. In the `private` section, add a field for the selected voice:
|
||||
|
||||
```cpp
|
||||
String _voice;
|
||||
```
|
||||
|
||||
1. To the `public` section, add an `init` function that will get the first voice:
|
||||
|
||||
```cpp
|
||||
void init()
|
||||
{
|
||||
}
|
||||
```
|
||||
|
||||
1. To get the voices, a JSON document needs to be sent to the function app with the language. Add the following code to the `init` function to create this JSON document:
|
||||
|
||||
```cpp
|
||||
DynamicJsonDocument doc(1024);
|
||||
doc["language"] = LANGUAGE;
|
||||
|
||||
String body;
|
||||
serializeJson(doc, body);
|
||||
```
|
||||
|
||||
1. Next create an `HTTPClient`, then use it to call the functions app to get the voices, posting the JSON document:
|
||||
|
||||
```cpp
|
||||
HTTPClient httpClient;
|
||||
httpClient.begin(_client, GET_VOICES_FUNCTION_URL);
|
||||
|
||||
int httpResponseCode = httpClient.POST(body);
|
||||
```
|
||||
|
||||
1. Below this add code to check the response code, and if it is 200 (success), then extract the list of voices, retrieving the first one from the list:
|
||||
|
||||
```cpp
|
||||
if (httpResponseCode == 200)
|
||||
{
|
||||
String result = httpClient.getString();
|
||||
Serial.println(result);
|
||||
|
||||
DynamicJsonDocument doc(1024);
|
||||
deserializeJson(doc, result.c_str());
|
||||
|
||||
JsonArray obj = doc.as<JsonArray>();
|
||||
_voice = obj[0].as<String>();
|
||||
|
||||
Serial.print("Using voice ");
|
||||
Serial.println(_voice);
|
||||
}
|
||||
else
|
||||
{
|
||||
Serial.print("Failed to get voices - error ");
|
||||
Serial.println(httpResponseCode);
|
||||
}
|
||||
```
|
||||
|
||||
1. After this, end the HTTP client connection:
|
||||
|
||||
```cpp
|
||||
httpClient.end();
|
||||
```
|
||||
|
||||
1. Open the `main.cpp` file, and add the following include directive at the top to include this new header file:
|
||||
|
||||
```cpp
|
||||
#include "text_to_speech.h"
|
||||
```
|
||||
|
||||
1. In the `setup` function, underneath the call to `speechToText.init();`, add the following to initialize the `TextToSpeech` class:
|
||||
|
||||
```cpp
|
||||
textToSpeech.init();
|
||||
```
|
||||
|
||||
1. Build this code, upload it to your Wio Terminal and test it out through the serial monitor. Make sure your function app is running.
|
||||
|
||||
You will see the list of available voices returned from the function app, along with the selected voice.
|
||||
|
||||
```output
|
||||
--- Available filters and text transformations: colorize, debug, default, direct, hexlify, log2file, nocontrol, printable, send_on_enter, time
|
||||
--- More details at http://bit.ly/pio-monitor-filters
|
||||
--- Miniterm on /dev/cu.usbmodem1101 9600,8,N,1 ---
|
||||
--- Quit: Ctrl+C | Menu: Ctrl+T | Help: Ctrl+T followed by Ctrl+H ---
|
||||
Connecting to WiFi..
|
||||
Connected!
|
||||
Got access token.
|
||||
["en-US-JennyNeural", "en-US-JennyMultilingualNeural", "en-US-GuyNeural", "en-US-AriaNeural", "en-US-AmberNeural", "en-US-AnaNeural", "en-US-AshleyNeural", "en-US-BrandonNeural", "en-US-ChristopherNeural", "en-US-CoraNeural", "en-US-ElizabethNeural", "en-US-EricNeural", "en-US-JacobNeural", "en-US-MichelleNeural", "en-US-MonicaNeural", "en-US-AriaRUS", "en-US-BenjaminRUS", "en-US-GuyRUS", "en-US-ZiraRUS"]
|
||||
Using voice en-US-JennyNeural
|
||||
Ready.
|
||||
```
|
||||
|
||||
## Convert text to speech
|
||||
|
||||
Once you have a voice to use, it can be used to convert text to speech. The same memory limitations with voices also apply when converting speech to text, so you will need to write the speech to an SD card ready to be played over the ReSpeaker.
|
||||
|
||||
> 💁 In earlier lessons in this project you used flash memory to store speech captured from the microphone. This lesson uses an SD card as is it easier to play audio from it using the Seeed audio libraries.
|
||||
|
||||
There is also another limitation to consider, the available audio data from the speech service, and the formats that the Wio Terminal supports. Unlike full computers, audio libraries for microcontrollers can be very limited in the audio formats they support. For example, the Seeed Arduino Audio library that can play sound over the ReSpeaker only supports audio at a 44.1KHz sample rate. The Azure speech services can provide audio in a number of formats, but none of them use this sample rate, they only provide 8KHz, 16KHz, 24KHz and 48KHz. This means the audio needs to be re-sampled to 44.1KHz, something that would need more resources that the Wio Terminal has, especially memory.
|
||||
|
||||
When needing to manipulate data like this, it is often better to use serverless code, especially if the data is sourced via a web call. The Wio Terminal can call a serverless function, passing in the text to convert, and the serverless function can both call the speech service to convert text to speech, as well as re-sample the audio to the required sample rate. It can then return the audio in the form the Wio Terminal needs to be stored on the SD card and played over the ReSpeaker.
|
||||
|
||||
### Task - create a serverless function to convert text to speech
|
||||
|
||||
1. Open your `smart-timer-trigger` project in VS Code, and open the terminal ensuring the virtual environment is activated. If not, kill and re-create the terminal.
|
||||
|
||||
1. Add a new HTTP trigger to this app called `text-to-speech` using the following command from inside the VS Code terminal in the root folder of the functions app project:
|
||||
|
||||
```sh
|
||||
func new --name text-to-speech --template "HTTP trigger"
|
||||
```
|
||||
|
||||
This will create an HTTP trigger called `text-to-speech`.
|
||||
|
||||
1. The [librosa](https://librosa.org) Pip package has functions to re-sample audio, so add this to the `requirements.txt` file:
|
||||
|
||||
```sh
|
||||
librosa
|
||||
```
|
||||
|
||||
Once this has been added, install the Pip packages using the following command from the VS Code terminal:
|
||||
|
||||
```sh
|
||||
pip install -r requirements.txt
|
||||
```
|
||||
|
||||
> ⚠️ If you are using Linux, including Raspberry Pi OS, you may need to install `libsndfile` with the following command:
|
||||
>
|
||||
> ```sh
|
||||
> sudo apt update
|
||||
> sudo apt install libsndfile1-dev
|
||||
> ```
|
||||
|
||||
1. To convert text to speech, you cannot use the speech API key directly, instead you need to request an access token, using the API key to authenticate the access token request. Open the `__init__.py` file from the `text-to-speech` folder and replace all the code in it with the following:
|
||||
|
||||
```python
|
||||
import io
|
||||
import os
|
||||
import requests
|
||||
|
||||
import librosa
|
||||
import soundfile as sf
|
||||
import azure.functions as func
|
||||
|
||||
location = os.environ['SPEECH_LOCATION']
|
||||
speech_key = os.environ['SPEECH_KEY']
|
||||
|
||||
def get_access_token():
|
||||
headers = {
|
||||
'Ocp-Apim-Subscription-Key': speech_key
|
||||
}
|
||||
|
||||
token_endpoint = f'https://{location}.api.cognitive.microsoft.com/sts/v1.0/issuetoken'
|
||||
response = requests.post(token_endpoint, headers=headers)
|
||||
return str(response.text)
|
||||
```
|
||||
|
||||
This defines constants for the location and speech key that will be read from the settings. It then defines the `get_access_token` function that will retrieve an access token for the speech service.
|
||||
|
||||
1. Below this code, add the following:
|
||||
|
||||
```python
|
||||
playback_format = 'riff-48khz-16bit-mono-pcm'
|
||||
|
||||
def main(req: func.HttpRequest) -> func.HttpResponse:
|
||||
req_body = req.get_json()
|
||||
language = req_body['language']
|
||||
voice = req_body['voice']
|
||||
text = req_body['text']
|
||||
|
||||
url = f'https://{location}.tts.speech.microsoft.com/cognitiveservices/v1'
|
||||
|
||||
headers = {
|
||||
'Authorization': 'Bearer ' + get_access_token(),
|
||||
'Content-Type': 'application/ssml+xml',
|
||||
'X-Microsoft-OutputFormat': playback_format
|
||||
}
|
||||
|
||||
ssml = f'<speak version=\'1.0\' xml:lang=\'{language}\'>'
|
||||
ssml += f'<voice xml:lang=\'{language}\' name=\'{voice}\'>'
|
||||
ssml += text
|
||||
ssml += '</voice>'
|
||||
ssml += '</speak>'
|
||||
|
||||
response = requests.post(url, headers=headers, data=ssml.encode('utf-8'))
|
||||
|
||||
raw_audio, sample_rate = librosa.load(io.BytesIO(response.content), sr=48000)
|
||||
resampled = librosa.resample(raw_audio, sample_rate, 44100)
|
||||
|
||||
output_buffer = io.BytesIO()
|
||||
sf.write(output_buffer, resampled, 44100, 'PCM_16', format='wav')
|
||||
output_buffer.seek(0)
|
||||
|
||||
return func.HttpResponse(output_buffer.read(), status_code=200)
|
||||
```
|
||||
|
||||
This defines the HTTP trigger that converts the text to speech. It extracts the text to convert, the language and the voice from the JSON body set to the request, builds some SSML to request the speech, then calls the relevant REST API authenticating using the access token. This REST API call returns the audio encoded as 16-bit, 48KHz mono WAV file, defined by the value of `playback_format`, which is sent to the REST API call.
|
||||
|
||||
This is then re-sampled by `librosa` from a sample rate of 48KHz to a sample rate of 44.1KHz, then this audio is saved to a binary buffer that is then returned.
|
||||
|
||||
1. Run your function app locally, or deploy it to the cloud. You can then call this using a tool like curl in the same way that you tested your `text-to-timer` HTTP trigger. Make sure to pass the language, voice and text as the JSON body:
|
||||
|
||||
```json
|
||||
{
|
||||
"language": "<language>",
|
||||
"voice": "<voice>",
|
||||
"text": "<text>"
|
||||
}
|
||||
```
|
||||
|
||||
Replace `<language>` with your language, such as `en-GB`, or `zh-CN`. Replace `<voice>` with the voice you want to use. Replace `<text>` with the text you want to convert to speech. You can save the output to a file and play it with any audio player that can play WAV files.
|
||||
|
||||
For example, to convert "Hello" to speech using US English with the Jenny Neural voice, with the function app running locally, you can use the following curl command:
|
||||
|
||||
```sh
|
||||
curl -X GET 'http://localhost:7071/api/text-to-speech' \
|
||||
-H 'Content-Type: application/json' \
|
||||
-o hello.wav \
|
||||
-d '{
|
||||
"language":"en-US",
|
||||
"voice": "en-US-JennyNeural",
|
||||
"text": "Hello"
|
||||
}'
|
||||
```
|
||||
|
||||
This will save the audio to `hello.wav` in the current directory.
|
||||
|
||||
> 💁 You can find this code in the [code-spoken-response/functions](code-spoken-response/functions) folder.
|
||||
|
||||
### Task - retrieve the speech from your Wio Terminal
|
||||
|
||||
1. Open the `smart-timer` project in VS Code if it is not already open.
|
||||
|
||||
1. Open the `config.h` header file and add the URL for your function app:
|
||||
|
||||
```cpp
|
||||
const char *TEXT_TO_SPEECH_FUNCTION_URL = "<URL>";
|
||||
```
|
||||
|
||||
Replace `<URL>` with the URL for the `text-to-speech` HTTP trigger on your function app. This will be the same as the value for `TEXT_TO_TIMER_FUNCTION_URL`, except with a function name of `text-to-speech` instead of `text-to-timer`.
|
||||
|
||||
1. Open the `text_to_speech.h` header file, and add the following method to the `public` section of the `TextToSpeech` class:
|
||||
|
||||
```cpp
|
||||
void convertTextToSpeech(String text)
|
||||
{
|
||||
}
|
||||
```
|
||||
|
||||
1. To the `convertTextToSpeech` method, add the following code to create the JSON to send to the function app:
|
||||
|
||||
```cpp
|
||||
DynamicJsonDocument doc(1024);
|
||||
doc["language"] = LANGUAGE;
|
||||
doc["voice"] = _voice;
|
||||
doc["text"] = text;
|
||||
|
||||
String body;
|
||||
serializeJson(doc, body);
|
||||
```
|
||||
|
||||
This writes the language, voice and text to the JSON document, then serializes it to a string.
|
||||
|
||||
1. Below this, add the following code to call the function app:
|
||||
|
||||
```cpp
|
||||
HTTPClient httpClient;
|
||||
httpClient.begin(_client, TEXT_TO_SPEECH_FUNCTION_URL);
|
||||
|
||||
int httpResponseCode = httpClient.POST(body);
|
||||
```
|
||||
|
||||
This creates an HTTPClient, then makes a POST request using the JSON document to the text to speech HTTP trigger.
|
||||
|
||||
1. If the call works, the raw binary data returned from the function app call can be streamed to a file on the SD card. Add the following code to do this:
|
||||
|
||||
```cpp
|
||||
if (httpResponseCode == 200)
|
||||
{
|
||||
File wav_file = SD.open("SPEECH.WAV", FILE_WRITE);
|
||||
httpClient.writeToStream(&wav_file);
|
||||
wav_file.close();
|
||||
}
|
||||
else
|
||||
{
|
||||
Serial.print("Failed to get speech - error ");
|
||||
Serial.println(httpResponseCode);
|
||||
}
|
||||
```
|
||||
|
||||
This code checks the response, and if it is 200 (success), the binary data is streamed to a file in the root of the SD Card called `SPEECH.WAV`.
|
||||
|
||||
1. At the end of this method, close the HTTP connection:
|
||||
|
||||
```cpp
|
||||
httpClient.end();
|
||||
```
|
||||
|
||||
1. The text to be spoken can now be converted to audio. In the `main.cpp` file, add the following line to the end of the `say` function to convert the text to say into audio:
|
||||
|
||||
```cpp
|
||||
textToSpeech.convertTextToSpeech(text);
|
||||
```
|
||||
|
||||
### Task - play audio from your Wio Terminal
|
||||
|
||||
**Coming soon**
|
||||
|
||||
## Deploying your functions app to the cloud
|
||||
|
||||
The reason for running the functions app locally is because the `librosa` Pip package on linux has a dependency on a library that is not installed by default, and will need to be installed before the function app can run. Function apps are serverless - there are no servers you can manage yourself, so no way to install this library up front.
|
||||
|
||||
The way to do this is instead to deploy your functions app using a Docker container. This container is deployed by the cloud whenever it needs to spin up a new instance of your function app (such as when the demand exceeds the available resources, or if the function app hasn't been used for a while and is closed down).
|
||||
|
||||
You can find the instructions to set up a function app and deploy via Docker in the [create a function on Linux using a custom container documentation on Microsoft Docs](https://docs.microsoft.com/azure/azure-functions/functions-create-function-linux-custom-image?tabs=bash%2Cazurecli&pivots=programming-language-python&WT.mc_id=academic-17441-jabenn).
|
||||
|
||||
Once this has been deployed, you can port your Wio Terminal code to access this function:
|
||||
|
||||
1. Add the Azure Functions certificate to `config.h`:
|
||||
|
||||
```cpp
|
||||
const char *FUNCTIONS_CERTIFICATE =
|
||||
"-----BEGIN CERTIFICATE-----\r\n"
|
||||
"MIIFWjCCBEKgAwIBAgIQDxSWXyAgaZlP1ceseIlB4jANBgkqhkiG9w0BAQsFADBa\r\n"
|
||||
"MQswCQYDVQQGEwJJRTESMBAGA1UEChMJQmFsdGltb3JlMRMwEQYDVQQLEwpDeWJl\r\n"
|
||||
"clRydXN0MSIwIAYDVQQDExlCYWx0aW1vcmUgQ3liZXJUcnVzdCBSb290MB4XDTIw\r\n"
|
||||
"MDcyMTIzMDAwMFoXDTI0MTAwODA3MDAwMFowTzELMAkGA1UEBhMCVVMxHjAcBgNV\r\n"
|
||||
"BAoTFU1pY3Jvc29mdCBDb3Jwb3JhdGlvbjEgMB4GA1UEAxMXTWljcm9zb2Z0IFJT\r\n"
|
||||
"QSBUTFMgQ0EgMDEwggIiMA0GCSqGSIb3DQEBAQUAA4ICDwAwggIKAoICAQCqYnfP\r\n"
|
||||
"mmOyBoTzkDb0mfMUUavqlQo7Rgb9EUEf/lsGWMk4bgj8T0RIzTqk970eouKVuL5R\r\n"
|
||||
"IMW/snBjXXgMQ8ApzWRJCZbar879BV8rKpHoAW4uGJssnNABf2n17j9TiFy6BWy+\r\n"
|
||||
"IhVnFILyLNK+W2M3zK9gheiWa2uACKhuvgCca5Vw/OQYErEdG7LBEzFnMzTmJcli\r\n"
|
||||
"W1iCdXby/vI/OxbfqkKD4zJtm45DJvC9Dh+hpzqvLMiK5uo/+aXSJY+SqhoIEpz+\r\n"
|
||||
"rErHw+uAlKuHFtEjSeeku8eR3+Z5ND9BSqc6JtLqb0bjOHPm5dSRrgt4nnil75bj\r\n"
|
||||
"c9j3lWXpBb9PXP9Sp/nPCK+nTQmZwHGjUnqlO9ebAVQD47ZisFonnDAmjrZNVqEX\r\n"
|
||||
"F3p7laEHrFMxttYuD81BdOzxAbL9Rb/8MeFGQjE2Qx65qgVfhH+RsYuuD9dUw/3w\r\n"
|
||||
"ZAhq05yO6nk07AM9c+AbNtRoEcdZcLCHfMDcbkXKNs5DJncCqXAN6LhXVERCw/us\r\n"
|
||||
"G2MmCMLSIx9/kwt8bwhUmitOXc6fpT7SmFvRAtvxg84wUkg4Y/Gx++0j0z6StSeN\r\n"
|
||||
"0EJz150jaHG6WV4HUqaWTb98Tm90IgXAU4AW2GBOlzFPiU5IY9jt+eXC2Q6yC/Zp\r\n"
|
||||
"TL1LAcnL3Qa/OgLrHN0wiw1KFGD51WRPQ0Sh7QIDAQABo4IBJTCCASEwHQYDVR0O\r\n"
|
||||
"BBYEFLV2DDARzseSQk1Mx1wsyKkM6AtkMB8GA1UdIwQYMBaAFOWdWTCCR1jMrPoI\r\n"
|
||||
"VDaGezq1BE3wMA4GA1UdDwEB/wQEAwIBhjAdBgNVHSUEFjAUBggrBgEFBQcDAQYI\r\n"
|
||||
"KwYBBQUHAwIwEgYDVR0TAQH/BAgwBgEB/wIBADA0BggrBgEFBQcBAQQoMCYwJAYI\r\n"
|
||||
"KwYBBQUHMAGGGGh0dHA6Ly9vY3NwLmRpZ2ljZXJ0LmNvbTA6BgNVHR8EMzAxMC+g\r\n"
|
||||
"LaArhilodHRwOi8vY3JsMy5kaWdpY2VydC5jb20vT21uaXJvb3QyMDI1LmNybDAq\r\n"
|
||||
"BgNVHSAEIzAhMAgGBmeBDAECATAIBgZngQwBAgIwCwYJKwYBBAGCNyoBMA0GCSqG\r\n"
|
||||
"SIb3DQEBCwUAA4IBAQCfK76SZ1vae4qt6P+dTQUO7bYNFUHR5hXcA2D59CJWnEj5\r\n"
|
||||
"na7aKzyowKvQupW4yMH9fGNxtsh6iJswRqOOfZYC4/giBO/gNsBvwr8uDW7t1nYo\r\n"
|
||||
"DYGHPpvnpxCM2mYfQFHq576/TmeYu1RZY29C4w8xYBlkAA8mDJfRhMCmehk7cN5F\r\n"
|
||||
"JtyWRj2cZj/hOoI45TYDBChXpOlLZKIYiG1giY16vhCRi6zmPzEwv+tk156N6cGS\r\n"
|
||||
"Vm44jTQ/rs1sa0JSYjzUaYngoFdZC4OfxnIkQvUIA4TOFmPzNPEFdjcZsgbeEz4T\r\n"
|
||||
"cGHTBPK4R28F44qIMCtHRV55VMX53ev6P3hRddJb\r\n"
|
||||
"-----END CERTIFICATE-----\r\n";
|
||||
```
|
||||
|
||||
1. Change all includes of `<WiFiClient.h>` to `<WiFiClientSecure.h>`.
|
||||
|
||||
1. Change all `WiFiClient` fields to `WiFiClientSecure`.
|
||||
|
||||
1. In every class that has a `WiFiClientSecure` field, add a constructor and set the certificate in that constructor:
|
||||
|
||||
```cpp
|
||||
_client.setCACert(FUNCTIONS_CERTIFICATE);
|
||||
```
|
||||
|
@ -0,0 +1,26 @@
|
||||
import json
|
||||
import os
|
||||
import requests
|
||||
|
||||
import azure.functions as func
|
||||
|
||||
def main(req: func.HttpRequest) -> func.HttpResponse:
|
||||
location = os.environ['SPEECH_LOCATION']
|
||||
speech_key = os.environ['SPEECH_KEY']
|
||||
|
||||
req_body = req.get_json()
|
||||
language = req_body['language']
|
||||
|
||||
url = f'https://{location}.tts.speech.microsoft.com/cognitiveservices/voices/list'
|
||||
|
||||
headers = {
|
||||
'Ocp-Apim-Subscription-Key': speech_key
|
||||
}
|
||||
|
||||
response = requests.get(url, headers=headers)
|
||||
voices_json = json.loads(response.text)
|
||||
|
||||
voices = filter(lambda x: x['Locale'].lower() == language.lower(), voices_json)
|
||||
voices = map(lambda x: x['ShortName'], voices)
|
||||
|
||||
return func.HttpResponse(json.dumps(list(voices)), status_code=200)
|
@ -0,0 +1,20 @@
|
||||
{
|
||||
"scriptFile": "__init__.py",
|
||||
"bindings": [
|
||||
{
|
||||
"authLevel": "function",
|
||||
"type": "httpTrigger",
|
||||
"direction": "in",
|
||||
"name": "req",
|
||||
"methods": [
|
||||
"get",
|
||||
"post"
|
||||
]
|
||||
},
|
||||
{
|
||||
"type": "http",
|
||||
"direction": "out",
|
||||
"name": "$return"
|
||||
}
|
||||
]
|
||||
}
|
@ -0,0 +1,15 @@
|
||||
{
|
||||
"version": "2.0",
|
||||
"logging": {
|
||||
"applicationInsights": {
|
||||
"samplingSettings": {
|
||||
"isEnabled": true,
|
||||
"excludedTypes": "Request"
|
||||
}
|
||||
}
|
||||
},
|
||||
"extensionBundle": {
|
||||
"id": "Microsoft.Azure.Functions.ExtensionBundle",
|
||||
"version": "[2.*, 3.0.0)"
|
||||
}
|
||||
}
|
@ -0,0 +1,14 @@
|
||||
{
|
||||
"IsEncrypted": false,
|
||||
"Values": {
|
||||
"FUNCTIONS_WORKER_RUNTIME": "python",
|
||||
"AzureWebJobsStorage": "",
|
||||
"LUIS_KEY": "<primary key>",
|
||||
"LUIS_ENDPOINT_URL": "<endpoint url>",
|
||||
"LUIS_APP_ID": "<app id>",
|
||||
"SPEECH_KEY": "<key>",
|
||||
"SPEECH_LOCATION": "<location>",
|
||||
"TRANSLATOR_KEY": "<key>",
|
||||
"TRANSLATOR_LOCATION": "<location>"
|
||||
}
|
||||
}
|
@ -0,0 +1,5 @@
|
||||
# Do not include azure-functions-worker as it may conflict with the Azure Functions platform
|
||||
|
||||
azure-functions
|
||||
azure-cognitiveservices-language-luis
|
||||
librosa
|
@ -0,0 +1,52 @@
|
||||
import io
|
||||
import os
|
||||
import requests
|
||||
|
||||
import librosa
|
||||
import soundfile as sf
|
||||
import azure.functions as func
|
||||
|
||||
location = os.environ['SPEECH_LOCATION']
|
||||
speech_key = os.environ['SPEECH_KEY']
|
||||
|
||||
def get_access_token():
|
||||
headers = {
|
||||
'Ocp-Apim-Subscription-Key': speech_key
|
||||
}
|
||||
|
||||
token_endpoint = f'https://{location}.api.cognitive.microsoft.com/sts/v1.0/issuetoken'
|
||||
response = requests.post(token_endpoint, headers=headers)
|
||||
return str(response.text)
|
||||
|
||||
playback_format = 'riff-48khz-16bit-mono-pcm'
|
||||
|
||||
def main(req: func.HttpRequest) -> func.HttpResponse:
|
||||
req_body = req.get_json()
|
||||
language = req_body['language']
|
||||
voice = req_body['voice']
|
||||
text = req_body['text']
|
||||
|
||||
url = f'https://{location}.tts.speech.microsoft.com/cognitiveservices/v1'
|
||||
|
||||
headers = {
|
||||
'Authorization': 'Bearer ' + get_access_token(),
|
||||
'Content-Type': 'application/ssml+xml',
|
||||
'X-Microsoft-OutputFormat': playback_format
|
||||
}
|
||||
|
||||
ssml = f'<speak version=\'1.0\' xml:lang=\'{language}\'>'
|
||||
ssml += f'<voice xml:lang=\'{language}\' name=\'{voice}\'>'
|
||||
ssml += text
|
||||
ssml += '</voice>'
|
||||
ssml += '</speak>'
|
||||
|
||||
response = requests.post(url, headers=headers, data=ssml.encode('utf-8'))
|
||||
|
||||
raw_audio, sample_rate = librosa.load(io.BytesIO(response.content), sr=48000)
|
||||
resampled = librosa.resample(raw_audio, sample_rate, 44100)
|
||||
|
||||
output_buffer = io.BytesIO()
|
||||
sf.write(output_buffer, resampled, 44100, 'PCM_16', format='wav')
|
||||
output_buffer.seek(0)
|
||||
|
||||
return func.HttpResponse(output_buffer.read(), status_code=200)
|
@ -0,0 +1,20 @@
|
||||
{
|
||||
"scriptFile": "__init__.py",
|
||||
"bindings": [
|
||||
{
|
||||
"authLevel": "function",
|
||||
"type": "httpTrigger",
|
||||
"direction": "in",
|
||||
"name": "req",
|
||||
"methods": [
|
||||
"get",
|
||||
"post"
|
||||
]
|
||||
},
|
||||
{
|
||||
"type": "http",
|
||||
"direction": "out",
|
||||
"name": "$return"
|
||||
}
|
||||
]
|
||||
}
|
@ -0,0 +1,46 @@
|
||||
import logging
|
||||
|
||||
import azure.functions as func
|
||||
import json
|
||||
import os
|
||||
from azure.cognitiveservices.language.luis.runtime import LUISRuntimeClient
|
||||
from msrest.authentication import CognitiveServicesCredentials
|
||||
|
||||
|
||||
def main(req: func.HttpRequest) -> func.HttpResponse:
|
||||
luis_key = os.environ['LUIS_KEY']
|
||||
endpoint_url = os.environ['LUIS_ENDPOINT_URL']
|
||||
app_id = os.environ['LUIS_APP_ID']
|
||||
|
||||
credentials = CognitiveServicesCredentials(luis_key)
|
||||
client = LUISRuntimeClient(endpoint=endpoint_url, credentials=credentials)
|
||||
|
||||
req_body = req.get_json()
|
||||
text = req_body['text']
|
||||
logging.info(f'Request - {text}')
|
||||
prediction_request = { 'query' : text }
|
||||
|
||||
prediction_response = client.prediction.get_slot_prediction(app_id, 'Staging', prediction_request)
|
||||
|
||||
if prediction_response.prediction.top_intent == 'set timer':
|
||||
numbers = prediction_response.prediction.entities['number']
|
||||
time_units = prediction_response.prediction.entities['time unit']
|
||||
total_seconds = 0
|
||||
|
||||
for i in range(0, len(numbers)):
|
||||
number = numbers[i]
|
||||
time_unit = time_units[i][0]
|
||||
|
||||
if time_unit == 'minute':
|
||||
total_seconds += number * 60
|
||||
else:
|
||||
total_seconds += number
|
||||
|
||||
logging.info(f'Timer required for {total_seconds} seconds')
|
||||
|
||||
payload = {
|
||||
'seconds': total_seconds
|
||||
}
|
||||
return func.HttpResponse(json.dumps(payload), status_code=200)
|
||||
|
||||
return func.HttpResponse(status_code=404)
|
@ -0,0 +1,20 @@
|
||||
{
|
||||
"scriptFile": "__init__.py",
|
||||
"bindings": [
|
||||
{
|
||||
"authLevel": "function",
|
||||
"type": "httpTrigger",
|
||||
"direction": "in",
|
||||
"name": "req",
|
||||
"methods": [
|
||||
"get",
|
||||
"post"
|
||||
]
|
||||
},
|
||||
{
|
||||
"type": "http",
|
||||
"direction": "out",
|
||||
"name": "$return"
|
||||
}
|
||||
]
|
||||
}
|
@ -0,0 +1,36 @@
|
||||
import logging
|
||||
import os
|
||||
import requests
|
||||
|
||||
import azure.functions as func
|
||||
|
||||
location = os.environ['TRANSLATOR_LOCATION']
|
||||
translator_key = os.environ['TRANSLATOR_KEY']
|
||||
|
||||
def main(req: func.HttpRequest) -> func.HttpResponse:
|
||||
req_body = req.get_json()
|
||||
from_language = req_body['from_language']
|
||||
to_language = req_body['to_language']
|
||||
text = req_body['text']
|
||||
|
||||
logging.info(f'Translating {text} from {from_language} to {to_language}')
|
||||
|
||||
url = f'https://api.cognitive.microsofttranslator.com/translate?api-version=3.0'
|
||||
|
||||
headers = {
|
||||
'Ocp-Apim-Subscription-Key': translator_key,
|
||||
'Ocp-Apim-Subscription-Region': location,
|
||||
'Content-type': 'application/json'
|
||||
}
|
||||
|
||||
params = {
|
||||
'from': from_language,
|
||||
'to': to_language
|
||||
}
|
||||
|
||||
body = [{
|
||||
'text' : text
|
||||
}]
|
||||
|
||||
response = requests.post(url, headers=headers, params=params, json=body)
|
||||
return func.HttpResponse(response.json()[0]['translations'][0]['text'])
|
Binary file not shown.
@ -0,0 +1,20 @@
|
||||
{
|
||||
"scriptFile": "__init__.py",
|
||||
"bindings": [
|
||||
{
|
||||
"authLevel": "function",
|
||||
"type": "httpTrigger",
|
||||
"direction": "in",
|
||||
"name": "req",
|
||||
"methods": [
|
||||
"get",
|
||||
"post"
|
||||
]
|
||||
},
|
||||
{
|
||||
"type": "http",
|
||||
"direction": "out",
|
||||
"name": "$return"
|
||||
}
|
||||
]
|
||||
}
|
@ -0,0 +1,39 @@
|
||||
|
||||
This directory is intended for project header files.
|
||||
|
||||
A header file is a file containing C declarations and macro definitions
|
||||
to be shared between several project source files. You request the use of a
|
||||
header file in your project source file (C, C++, etc) located in `src` folder
|
||||
by including it, with the C preprocessing directive `#include'.
|
||||
|
||||
```src/main.c
|
||||
|
||||
#include "header.h"
|
||||
|
||||
int main (void)
|
||||
{
|
||||
...
|
||||
}
|
||||
```
|
||||
|
||||
Including a header file produces the same results as copying the header file
|
||||
into each source file that needs it. Such copying would be time-consuming
|
||||
and error-prone. With a header file, the related declarations appear
|
||||
in only one place. If they need to be changed, they can be changed in one
|
||||
place, and programs that include the header file will automatically use the
|
||||
new version when next recompiled. The header file eliminates the labor of
|
||||
finding and changing all the copies as well as the risk that a failure to
|
||||
find one copy will result in inconsistencies within a program.
|
||||
|
||||
In C, the usual convention is to give header files names that end with `.h'.
|
||||
It is most portable to use only letters, digits, dashes, and underscores in
|
||||
header file names, and at most one dot.
|
||||
|
||||
Read more about using header files in official GCC documentation:
|
||||
|
||||
* Include Syntax
|
||||
* Include Operation
|
||||
* Once-Only Headers
|
||||
* Computed Includes
|
||||
|
||||
https://gcc.gnu.org/onlinedocs/cpp/Header-Files.html
|
@ -0,0 +1,46 @@
|
||||
|
||||
This directory is intended for project specific (private) libraries.
|
||||
PlatformIO will compile them to static libraries and link into executable file.
|
||||
|
||||
The source code of each library should be placed in a an own separate directory
|
||||
("lib/your_library_name/[here are source files]").
|
||||
|
||||
For example, see a structure of the following two libraries `Foo` and `Bar`:
|
||||
|
||||
|--lib
|
||||
| |
|
||||
| |--Bar
|
||||
| | |--docs
|
||||
| | |--examples
|
||||
| | |--src
|
||||
| | |- Bar.c
|
||||
| | |- Bar.h
|
||||
| | |- library.json (optional, custom build options, etc) https://docs.platformio.org/page/librarymanager/config.html
|
||||
| |
|
||||
| |--Foo
|
||||
| | |- Foo.c
|
||||
| | |- Foo.h
|
||||
| |
|
||||
| |- README --> THIS FILE
|
||||
|
|
||||
|- platformio.ini
|
||||
|--src
|
||||
|- main.c
|
||||
|
||||
and a contents of `src/main.c`:
|
||||
```
|
||||
#include <Foo.h>
|
||||
#include <Bar.h>
|
||||
|
||||
int main (void)
|
||||
{
|
||||
...
|
||||
}
|
||||
|
||||
```
|
||||
|
||||
PlatformIO Library Dependency Finder will find automatically dependent
|
||||
libraries scanning project source files.
|
||||
|
||||
More information about PlatformIO Library Dependency Finder
|
||||
- https://docs.platformio.org/page/librarymanager/ldf.html
|
@ -0,0 +1,23 @@
|
||||
; PlatformIO Project Configuration File
|
||||
;
|
||||
; Build options: build flags, source filter
|
||||
; Upload options: custom upload port, speed and extra flags
|
||||
; Library options: dependencies, extra library storages
|
||||
; Advanced options: extra scripting
|
||||
;
|
||||
; Please visit documentation for the other options and examples
|
||||
; https://docs.platformio.org/page/projectconf.html
|
||||
|
||||
[env:seeed_wio_terminal]
|
||||
platform = atmelsam
|
||||
board = seeed_wio_terminal
|
||||
framework = arduino
|
||||
lib_deps =
|
||||
seeed-studio/Seeed Arduino FS @ 2.1.1
|
||||
seeed-studio/Seeed Arduino SFUD @ 2.0.2
|
||||
seeed-studio/Seeed Arduino rpcWiFi @ 1.0.5
|
||||
seeed-studio/Seeed Arduino rpcUnified @ 2.1.3
|
||||
seeed-studio/Seeed_Arduino_mbedtls @ 3.0.1
|
||||
seeed-studio/Seeed Arduino RTC @ 2.0.0
|
||||
bblanchon/ArduinoJson @ 6.17.3
|
||||
contrem/arduino-timer @ 2.3.0
|
@ -0,0 +1,95 @@
|
||||
#pragma once
|
||||
|
||||
#define RATE 16000
|
||||
#define SAMPLE_LENGTH_SECONDS 4
|
||||
#define SAMPLES RATE * SAMPLE_LENGTH_SECONDS
|
||||
#define BUFFER_SIZE (SAMPLES * 2) + 44
|
||||
#define ADC_BUF_LEN 1600
|
||||
|
||||
const char *SSID = "<SSID>";
|
||||
const char *PASSWORD = "<PASSWORD>";
|
||||
|
||||
const char *SPEECH_API_KEY = "<API_KEY>";
|
||||
const char *SPEECH_LOCATION = "<LOCATION>";
|
||||
const char *LANGUAGE = "<LANGUAGE>";
|
||||
const char *SERVER_LANGUAGE = "<LANGUAGE>";
|
||||
|
||||
const char *TOKEN_URL = "https://%s.api.cognitive.microsoft.com/sts/v1.0/issuetoken";
|
||||
const char *SPEECH_URL = "https://%s.stt.speech.microsoft.com/speech/recognition/conversation/cognitiveservices/v1?language=%s";
|
||||
|
||||
const char *TEXT_TO_TIMER_FUNCTION_URL = "http://<IP_ADDRESS>:7071/api/text-to-timer";
|
||||
const char *GET_VOICES_FUNCTION_URL = "http://<IP_ADDRESS>:7071/api/get-voices";
|
||||
const char *TEXT_TO_SPEECH_FUNCTION_URL = "http://<IP_ADDRESS>:7071/api/text-to-speech";
|
||||
const char *TRANSLATE_FUNCTION_URL = "http://<IP_ADDRESS>:7071/api/translate-text";
|
||||
|
||||
const char *TOKEN_CERTIFICATE =
|
||||
"-----BEGIN CERTIFICATE-----\r\n"
|
||||
"MIIF8zCCBNugAwIBAgIQAueRcfuAIek/4tmDg0xQwDANBgkqhkiG9w0BAQwFADBh\r\n"
|
||||
"MQswCQYDVQQGEwJVUzEVMBMGA1UEChMMRGlnaUNlcnQgSW5jMRkwFwYDVQQLExB3\r\n"
|
||||
"d3cuZGlnaWNlcnQuY29tMSAwHgYDVQQDExdEaWdpQ2VydCBHbG9iYWwgUm9vdCBH\r\n"
|
||||
"MjAeFw0yMDA3MjkxMjMwMDBaFw0yNDA2MjcyMzU5NTlaMFkxCzAJBgNVBAYTAlVT\r\n"
|
||||
"MR4wHAYDVQQKExVNaWNyb3NvZnQgQ29ycG9yYXRpb24xKjAoBgNVBAMTIU1pY3Jv\r\n"
|
||||
"c29mdCBBenVyZSBUTFMgSXNzdWluZyBDQSAwNjCCAiIwDQYJKoZIhvcNAQEBBQAD\r\n"
|
||||
"ggIPADCCAgoCggIBALVGARl56bx3KBUSGuPc4H5uoNFkFH4e7pvTCxRi4j/+z+Xb\r\n"
|
||||
"wjEz+5CipDOqjx9/jWjskL5dk7PaQkzItidsAAnDCW1leZBOIi68Lff1bjTeZgMY\r\n"
|
||||
"iwdRd3Y39b/lcGpiuP2d23W95YHkMMT8IlWosYIX0f4kYb62rphyfnAjYb/4Od99\r\n"
|
||||
"ThnhlAxGtfvSbXcBVIKCYfZgqRvV+5lReUnd1aNjRYVzPOoifgSx2fRyy1+pO1Uz\r\n"
|
||||
"aMMNnIOE71bVYW0A1hr19w7kOb0KkJXoALTDDj1ukUEDqQuBfBxReL5mXiu1O7WG\r\n"
|
||||
"0vltg0VZ/SZzctBsdBlx1BkmWYBW261KZgBivrql5ELTKKd8qgtHcLQA5fl6JB0Q\r\n"
|
||||
"gs5XDaWehN86Gps5JW8ArjGtjcWAIP+X8CQaWfaCnuRm6Bk/03PQWhgdi84qwA0s\r\n"
|
||||
"sRfFJwHUPTNSnE8EiGVk2frt0u8PG1pwSQsFuNJfcYIHEv1vOzP7uEOuDydsmCjh\r\n"
|
||||
"lxuoK2n5/2aVR3BMTu+p4+gl8alXoBycyLmj3J/PUgqD8SL5fTCUegGsdia/Sa60\r\n"
|
||||
"N2oV7vQ17wjMN+LXa2rjj/b4ZlZgXVojDmAjDwIRdDUujQu0RVsJqFLMzSIHpp2C\r\n"
|
||||
"Zp7mIoLrySay2YYBu7SiNwL95X6He2kS8eefBBHjzwW/9FxGqry57i71c2cDAgMB\r\n"
|
||||
"AAGjggGtMIIBqTAdBgNVHQ4EFgQU1cFnOsKjnfR3UltZEjgp5lVou6UwHwYDVR0j\r\n"
|
||||
"BBgwFoAUTiJUIBiV5uNu5g/6+rkS7QYXjzkwDgYDVR0PAQH/BAQDAgGGMB0GA1Ud\r\n"
|
||||
"JQQWMBQGCCsGAQUFBwMBBggrBgEFBQcDAjASBgNVHRMBAf8ECDAGAQH/AgEAMHYG\r\n"
|
||||
"CCsGAQUFBwEBBGowaDAkBggrBgEFBQcwAYYYaHR0cDovL29jc3AuZGlnaWNlcnQu\r\n"
|
||||
"Y29tMEAGCCsGAQUFBzAChjRodHRwOi8vY2FjZXJ0cy5kaWdpY2VydC5jb20vRGln\r\n"
|
||||
"aUNlcnRHbG9iYWxSb290RzIuY3J0MHsGA1UdHwR0MHIwN6A1oDOGMWh0dHA6Ly9j\r\n"
|
||||
"cmwzLmRpZ2ljZXJ0LmNvbS9EaWdpQ2VydEdsb2JhbFJvb3RHMi5jcmwwN6A1oDOG\r\n"
|
||||
"MWh0dHA6Ly9jcmw0LmRpZ2ljZXJ0LmNvbS9EaWdpQ2VydEdsb2JhbFJvb3RHMi5j\r\n"
|
||||
"cmwwHQYDVR0gBBYwFDAIBgZngQwBAgEwCAYGZ4EMAQICMBAGCSsGAQQBgjcVAQQD\r\n"
|
||||
"AgEAMA0GCSqGSIb3DQEBDAUAA4IBAQB2oWc93fB8esci/8esixj++N22meiGDjgF\r\n"
|
||||
"+rA2LUK5IOQOgcUSTGKSqF9lYfAxPjrqPjDCUPHCURv+26ad5P/BYtXtbmtxJWu+\r\n"
|
||||
"cS5BhMDPPeG3oPZwXRHBJFAkY4O4AF7RIAAUW6EzDflUoDHKv83zOiPfYGcpHc9s\r\n"
|
||||
"kxAInCedk7QSgXvMARjjOqdakor21DTmNIUotxo8kHv5hwRlGhBJwps6fEVi1Bt0\r\n"
|
||||
"trpM/3wYxlr473WSPUFZPgP1j519kLpWOJ8z09wxay+Br29irPcBYv0GMXlHqThy\r\n"
|
||||
"8y4m/HyTQeI2IMvMrQnwqPpY+rLIXyviI2vLoI+4xKE4Rn38ZZ8m\r\n"
|
||||
"-----END CERTIFICATE-----\r\n";
|
||||
|
||||
const char *SPEECH_CERTIFICATE =
|
||||
"-----BEGIN CERTIFICATE-----\r\n"
|
||||
"MIIF8zCCBNugAwIBAgIQCq+mxcpjxFFB6jvh98dTFzANBgkqhkiG9w0BAQwFADBh\r\n"
|
||||
"MQswCQYDVQQGEwJVUzEVMBMGA1UEChMMRGlnaUNlcnQgSW5jMRkwFwYDVQQLExB3\r\n"
|
||||
"d3cuZGlnaWNlcnQuY29tMSAwHgYDVQQDExdEaWdpQ2VydCBHbG9iYWwgUm9vdCBH\r\n"
|
||||
"MjAeFw0yMDA3MjkxMjMwMDBaFw0yNDA2MjcyMzU5NTlaMFkxCzAJBgNVBAYTAlVT\r\n"
|
||||
"MR4wHAYDVQQKExVNaWNyb3NvZnQgQ29ycG9yYXRpb24xKjAoBgNVBAMTIU1pY3Jv\r\n"
|
||||
"c29mdCBBenVyZSBUTFMgSXNzdWluZyBDQSAwMTCCAiIwDQYJKoZIhvcNAQEBBQAD\r\n"
|
||||
"ggIPADCCAgoCggIBAMedcDrkXufP7pxVm1FHLDNA9IjwHaMoaY8arqqZ4Gff4xyr\r\n"
|
||||
"RygnavXL7g12MPAx8Q6Dd9hfBzrfWxkF0Br2wIvlvkzW01naNVSkHp+OS3hL3W6n\r\n"
|
||||
"l/jYvZnVeJXjtsKYcXIf/6WtspcF5awlQ9LZJcjwaH7KoZuK+THpXCMtzD8XNVdm\r\n"
|
||||
"GW/JI0C/7U/E7evXn9XDio8SYkGSM63aLO5BtLCv092+1d4GGBSQYolRq+7Pd1kR\r\n"
|
||||
"EkWBPm0ywZ2Vb8GIS5DLrjelEkBnKCyy3B0yQud9dpVsiUeE7F5sY8Me96WVxQcb\r\n"
|
||||
"OyYdEY/j/9UpDlOG+vA+YgOvBhkKEjiqygVpP8EZoMMijephzg43b5Qi9r5UrvYo\r\n"
|
||||
"o19oR/8pf4HJNDPF0/FJwFVMW8PmCBLGstin3NE1+NeWTkGt0TzpHjgKyfaDP2tO\r\n"
|
||||
"4bCk1G7pP2kDFT7SYfc8xbgCkFQ2UCEXsaH/f5YmpLn4YPiNFCeeIida7xnfTvc4\r\n"
|
||||
"7IxyVccHHq1FzGygOqemrxEETKh8hvDR6eBdrBwmCHVgZrnAqnn93JtGyPLi6+cj\r\n"
|
||||
"WGVGtMZHwzVvX1HvSFG771sskcEjJxiQNQDQRWHEh3NxvNb7kFlAXnVdRkkvhjpR\r\n"
|
||||
"GchFhTAzqmwltdWhWDEyCMKC2x/mSZvZtlZGY+g37Y72qHzidwtyW7rBetZJAgMB\r\n"
|
||||
"AAGjggGtMIIBqTAdBgNVHQ4EFgQUDyBd16FXlduSzyvQx8J3BM5ygHYwHwYDVR0j\r\n"
|
||||
"BBgwFoAUTiJUIBiV5uNu5g/6+rkS7QYXjzkwDgYDVR0PAQH/BAQDAgGGMB0GA1Ud\r\n"
|
||||
"JQQWMBQGCCsGAQUFBwMBBggrBgEFBQcDAjASBgNVHRMBAf8ECDAGAQH/AgEAMHYG\r\n"
|
||||
"CCsGAQUFBwEBBGowaDAkBggrBgEFBQcwAYYYaHR0cDovL29jc3AuZGlnaWNlcnQu\r\n"
|
||||
"Y29tMEAGCCsGAQUFBzAChjRodHRwOi8vY2FjZXJ0cy5kaWdpY2VydC5jb20vRGln\r\n"
|
||||
"aUNlcnRHbG9iYWxSb290RzIuY3J0MHsGA1UdHwR0MHIwN6A1oDOGMWh0dHA6Ly9j\r\n"
|
||||
"cmwzLmRpZ2ljZXJ0LmNvbS9EaWdpQ2VydEdsb2JhbFJvb3RHMi5jcmwwN6A1oDOG\r\n"
|
||||
"MWh0dHA6Ly9jcmw0LmRpZ2ljZXJ0LmNvbS9EaWdpQ2VydEdsb2JhbFJvb3RHMi5j\r\n"
|
||||
"cmwwHQYDVR0gBBYwFDAIBgZngQwBAgEwCAYGZ4EMAQICMBAGCSsGAQQBgjcVAQQD\r\n"
|
||||
"AgEAMA0GCSqGSIb3DQEBDAUAA4IBAQAlFvNh7QgXVLAZSsNR2XRmIn9iS8OHFCBA\r\n"
|
||||
"WxKJoi8YYQafpMTkMqeuzoL3HWb1pYEipsDkhiMnrpfeYZEA7Lz7yqEEtfgHcEBs\r\n"
|
||||
"K9KcStQGGZRfmWU07hPXHnFz+5gTXqzCE2PBMlRgVUYJiA25mJPXfB00gDvGhtYa\r\n"
|
||||
"+mENwM9Bq1B9YYLyLjRtUz8cyGsdyTIG/bBM/Q9jcV8JGqMU/UjAdh1pFyTnnHEl\r\n"
|
||||
"Y59Npi7F87ZqYYJEHJM2LGD+le8VsHjgeWX2CJQko7klXvcizuZvUEDTjHaQcs2J\r\n"
|
||||
"+kPgfyMIOY1DMJ21NxOJ2xPRC/wAh/hzSBRVtoAnyuxtkZ4VjIOh\r\n"
|
||||
"-----END CERTIFICATE-----\r\n";
|
@ -0,0 +1,69 @@
|
||||
#pragma once
|
||||
|
||||
#include <Arduino.h>
|
||||
#include <HTTPClient.h>
|
||||
#include <sfud.h>
|
||||
|
||||
#include "config.h"
|
||||
|
||||
class FlashStream : public Stream
|
||||
{
|
||||
public:
|
||||
FlashStream()
|
||||
{
|
||||
_pos = 0;
|
||||
_flash_address = 0;
|
||||
_flash = sfud_get_device_table() + 0;
|
||||
|
||||
populateBuffer();
|
||||
}
|
||||
|
||||
virtual size_t write(uint8_t val)
|
||||
{
|
||||
return 0;
|
||||
}
|
||||
|
||||
virtual int available()
|
||||
{
|
||||
int remaining = BUFFER_SIZE - ((_flash_address - HTTP_TCP_BUFFER_SIZE) + _pos);
|
||||
int bytes_available = min(HTTP_TCP_BUFFER_SIZE, remaining);
|
||||
|
||||
if (bytes_available == 0)
|
||||
{
|
||||
bytes_available = -1;
|
||||
}
|
||||
|
||||
return bytes_available;
|
||||
}
|
||||
|
||||
virtual int read()
|
||||
{
|
||||
int retVal = _buffer[_pos++];
|
||||
|
||||
if (_pos == HTTP_TCP_BUFFER_SIZE)
|
||||
{
|
||||
populateBuffer();
|
||||
}
|
||||
|
||||
return retVal;
|
||||
}
|
||||
|
||||
virtual int peek()
|
||||
{
|
||||
return _buffer[_pos];
|
||||
}
|
||||
|
||||
private:
|
||||
void populateBuffer()
|
||||
{
|
||||
sfud_read(_flash, _flash_address, HTTP_TCP_BUFFER_SIZE, _buffer);
|
||||
_flash_address += HTTP_TCP_BUFFER_SIZE;
|
||||
_pos = 0;
|
||||
}
|
||||
|
||||
size_t _pos;
|
||||
size_t _flash_address;
|
||||
const sfud_flash *_flash;
|
||||
|
||||
byte _buffer[HTTP_TCP_BUFFER_SIZE];
|
||||
};
|
@ -0,0 +1,60 @@
|
||||
#pragma once
|
||||
|
||||
#include <Arduino.h>
|
||||
#include <sfud.h>
|
||||
|
||||
class FlashWriter
|
||||
{
|
||||
public:
|
||||
void init()
|
||||
{
|
||||
_flash = sfud_get_device_table() + 0;
|
||||
_sfudBufferSize = _flash->chip.erase_gran;
|
||||
_sfudBuffer = new byte[_sfudBufferSize];
|
||||
_sfudBufferPos = 0;
|
||||
_sfudBufferWritePos = 0;
|
||||
}
|
||||
|
||||
void reset()
|
||||
{
|
||||
_sfudBufferPos = 0;
|
||||
_sfudBufferWritePos = 0;
|
||||
}
|
||||
|
||||
void writeSfudBuffer(byte b)
|
||||
{
|
||||
_sfudBuffer[_sfudBufferPos++] = b;
|
||||
if (_sfudBufferPos == _sfudBufferSize)
|
||||
{
|
||||
sfud_erase_write(_flash, _sfudBufferWritePos, _sfudBufferSize, _sfudBuffer);
|
||||
_sfudBufferWritePos += _sfudBufferSize;
|
||||
_sfudBufferPos = 0;
|
||||
}
|
||||
}
|
||||
|
||||
void flushSfudBuffer()
|
||||
{
|
||||
if (_sfudBufferPos > 0)
|
||||
{
|
||||
sfud_erase_write(_flash, _sfudBufferWritePos, _sfudBufferSize, _sfudBuffer);
|
||||
_sfudBufferWritePos += _sfudBufferSize;
|
||||
_sfudBufferPos = 0;
|
||||
}
|
||||
}
|
||||
|
||||
void writeSfudBuffer(byte *b, size_t len)
|
||||
{
|
||||
for (size_t i = 0; i < len; ++i)
|
||||
{
|
||||
writeSfudBuffer(b[i]);
|
||||
}
|
||||
}
|
||||
|
||||
private:
|
||||
byte *_sfudBuffer;
|
||||
size_t _sfudBufferSize;
|
||||
size_t _sfudBufferPos;
|
||||
size_t _sfudBufferWritePos;
|
||||
|
||||
const sfud_flash *_flash;
|
||||
};
|
@ -0,0 +1,53 @@
|
||||
#pragma once
|
||||
|
||||
#include <Arduino.h>
|
||||
#include <ArduinoJson.h>
|
||||
#include <HTTPClient.h>
|
||||
#include <WiFiClient.h>
|
||||
|
||||
#include "config.h"
|
||||
|
||||
class LanguageUnderstanding
|
||||
{
|
||||
public:
|
||||
int GetTimerDuration(String text)
|
||||
{
|
||||
DynamicJsonDocument doc(1024);
|
||||
doc["text"] = text;
|
||||
|
||||
String body;
|
||||
serializeJson(doc, body);
|
||||
|
||||
HTTPClient httpClient;
|
||||
httpClient.begin(_client, TEXT_TO_TIMER_FUNCTION_URL);
|
||||
|
||||
int httpResponseCode = httpClient.POST(body);
|
||||
|
||||
int seconds = 0;
|
||||
if (httpResponseCode == 200)
|
||||
{
|
||||
String result = httpClient.getString();
|
||||
Serial.println(result);
|
||||
|
||||
DynamicJsonDocument doc(1024);
|
||||
deserializeJson(doc, result.c_str());
|
||||
|
||||
JsonObject obj = doc.as<JsonObject>();
|
||||
seconds = obj["seconds"].as<int>();
|
||||
}
|
||||
else
|
||||
{
|
||||
Serial.print("Failed to understand text - error ");
|
||||
Serial.println(httpResponseCode);
|
||||
}
|
||||
|
||||
httpClient.end();
|
||||
|
||||
return seconds;
|
||||
}
|
||||
|
||||
private:
|
||||
WiFiClient _client;
|
||||
};
|
||||
|
||||
LanguageUnderstanding languageUnderstanding;
|
@ -0,0 +1,133 @@
|
||||
#include <Arduino.h>
|
||||
#include <arduino-timer.h>
|
||||
#include <rpcWiFi.h>
|
||||
#include <sfud.h>
|
||||
#include <SPI.h>
|
||||
|
||||
#include "config.h"
|
||||
#include "language_understanding.h"
|
||||
#include "mic.h"
|
||||
#include "speech_to_text.h"
|
||||
#include "text_to_speech.h"
|
||||
#include "text_translator.h"
|
||||
|
||||
void connectWiFi()
|
||||
{
|
||||
while (WiFi.status() != WL_CONNECTED)
|
||||
{
|
||||
Serial.println("Connecting to WiFi..");
|
||||
WiFi.begin(SSID, PASSWORD);
|
||||
delay(500);
|
||||
}
|
||||
|
||||
Serial.println("Connected!");
|
||||
}
|
||||
|
||||
void setup()
|
||||
{
|
||||
Serial.begin(9600);
|
||||
|
||||
while (!Serial)
|
||||
; // Wait for Serial to be ready
|
||||
|
||||
delay(1000);
|
||||
|
||||
connectWiFi();
|
||||
|
||||
while (!(sfud_init() == SFUD_SUCCESS))
|
||||
;
|
||||
|
||||
sfud_qspi_fast_read_enable(sfud_get_device(SFUD_W25Q32_DEVICE_INDEX), 2);
|
||||
|
||||
pinMode(WIO_KEY_C, INPUT_PULLUP);
|
||||
|
||||
mic.init();
|
||||
|
||||
speechToText.init();
|
||||
textToSpeech.init();
|
||||
|
||||
Serial.println("Ready.");
|
||||
}
|
||||
|
||||
auto timer = timer_create_default();
|
||||
|
||||
void say(String text)
|
||||
{
|
||||
text = textTranslator.translateText(text, SERVER_LANGUAGE, LANGUAGE);
|
||||
Serial.println(text);
|
||||
textToSpeech.convertTextToSpeech(text);
|
||||
}
|
||||
|
||||
bool timerExpired(void *announcement)
|
||||
{
|
||||
say((char *)announcement);
|
||||
return false;
|
||||
}
|
||||
|
||||
void processAudio()
|
||||
{
|
||||
String text = speechToText.convertSpeechToText();
|
||||
text = textTranslator.translateText(text, LANGUAGE, SERVER_LANGUAGE);
|
||||
Serial.println(text);
|
||||
|
||||
int total_seconds = languageUnderstanding.GetTimerDuration(text);
|
||||
if (total_seconds == 0)
|
||||
{
|
||||
return;
|
||||
}
|
||||
|
||||
int minutes = total_seconds / 60;
|
||||
int seconds = total_seconds % 60;
|
||||
|
||||
String begin_message;
|
||||
if (minutes > 0)
|
||||
{
|
||||
begin_message += minutes;
|
||||
begin_message += " minute ";
|
||||
}
|
||||
if (seconds > 0)
|
||||
{
|
||||
begin_message += seconds;
|
||||
begin_message += " second ";
|
||||
}
|
||||
|
||||
begin_message += "timer started.";
|
||||
|
||||
String end_message("Times up on your ");
|
||||
if (minutes > 0)
|
||||
{
|
||||
end_message += minutes;
|
||||
end_message += " minute ";
|
||||
}
|
||||
if (seconds > 0)
|
||||
{
|
||||
end_message += seconds;
|
||||
end_message += " second ";
|
||||
}
|
||||
|
||||
end_message += "timer.";
|
||||
|
||||
say(begin_message);
|
||||
|
||||
timer.in(total_seconds * 1000, timerExpired, (void *)(end_message.c_str()));
|
||||
}
|
||||
|
||||
void loop()
|
||||
{
|
||||
if (digitalRead(WIO_KEY_C) == LOW && !mic.isRecording())
|
||||
{
|
||||
Serial.println("Starting recording...");
|
||||
mic.startRecording();
|
||||
}
|
||||
|
||||
if (!mic.isRecording() && mic.isRecordingReady())
|
||||
{
|
||||
Serial.println("Finished recording");
|
||||
|
||||
processAudio();
|
||||
|
||||
mic.reset();
|
||||
}
|
||||
|
||||
timer.tick();
|
||||
}
|
@ -0,0 +1,242 @@
|
||||
#pragma once
|
||||
|
||||
#include <Arduino.h>
|
||||
|
||||
#include "config.h"
|
||||
#include "flash_writer.h"
|
||||
|
||||
class Mic
|
||||
{
|
||||
public:
|
||||
Mic()
|
||||
{
|
||||
_isRecording = false;
|
||||
_isRecordingReady = false;
|
||||
}
|
||||
|
||||
void startRecording()
|
||||
{
|
||||
_isRecording = true;
|
||||
_isRecordingReady = false;
|
||||
}
|
||||
|
||||
bool isRecording()
|
||||
{
|
||||
return _isRecording;
|
||||
}
|
||||
|
||||
bool isRecordingReady()
|
||||
{
|
||||
return _isRecordingReady;
|
||||
}
|
||||
|
||||
void init()
|
||||
{
|
||||
analogReference(AR_INTERNAL2V23);
|
||||
|
||||
_writer.init();
|
||||
|
||||
initBufferHeader();
|
||||
configureDmaAdc();
|
||||
}
|
||||
|
||||
void reset()
|
||||
{
|
||||
_isRecordingReady = false;
|
||||
_isRecording = false;
|
||||
|
||||
_writer.reset();
|
||||
|
||||
initBufferHeader();
|
||||
}
|
||||
|
||||
void dmaHandler()
|
||||
{
|
||||
static uint8_t count = 0;
|
||||
|
||||
if (DMAC->Channel[1].CHINTFLAG.bit.SUSP)
|
||||
{
|
||||
DMAC->Channel[1].CHCTRLB.reg = DMAC_CHCTRLB_CMD_RESUME;
|
||||
DMAC->Channel[1].CHINTFLAG.bit.SUSP = 1;
|
||||
|
||||
if (count)
|
||||
{
|
||||
audioCallback(_adc_buf_0, ADC_BUF_LEN);
|
||||
}
|
||||
else
|
||||
{
|
||||
audioCallback(_adc_buf_1, ADC_BUF_LEN);
|
||||
}
|
||||
|
||||
count = (count + 1) % 2;
|
||||
}
|
||||
}
|
||||
|
||||
private:
|
||||
volatile bool _isRecording;
|
||||
volatile bool _isRecordingReady;
|
||||
FlashWriter _writer;
|
||||
|
||||
typedef struct
|
||||
{
|
||||
uint16_t btctrl;
|
||||
uint16_t btcnt;
|
||||
uint32_t srcaddr;
|
||||
uint32_t dstaddr;
|
||||
uint32_t descaddr;
|
||||
} dmacdescriptor;
|
||||
|
||||
// Globals - DMA and ADC
|
||||
volatile dmacdescriptor _wrb[DMAC_CH_NUM] __attribute__((aligned(16)));
|
||||
dmacdescriptor _descriptor_section[DMAC_CH_NUM] __attribute__((aligned(16)));
|
||||
dmacdescriptor _descriptor __attribute__((aligned(16)));
|
||||
|
||||
void configureDmaAdc()
|
||||
{
|
||||
// Configure DMA to sample from ADC at a regular interval (triggered by timer/counter)
|
||||
DMAC->BASEADDR.reg = (uint32_t)_descriptor_section; // Specify the location of the descriptors
|
||||
DMAC->WRBADDR.reg = (uint32_t)_wrb; // Specify the location of the write back descriptors
|
||||
DMAC->CTRL.reg = DMAC_CTRL_DMAENABLE | DMAC_CTRL_LVLEN(0xf); // Enable the DMAC peripheral
|
||||
DMAC->Channel[1].CHCTRLA.reg = DMAC_CHCTRLA_TRIGSRC(TC5_DMAC_ID_OVF) | // Set DMAC to trigger on TC5 timer overflow
|
||||
DMAC_CHCTRLA_TRIGACT_BURST; // DMAC burst transfer
|
||||
|
||||
_descriptor.descaddr = (uint32_t)&_descriptor_section[1]; // Set up a circular descriptor
|
||||
_descriptor.srcaddr = (uint32_t)&ADC1->RESULT.reg; // Take the result from the ADC0 RESULT register
|
||||
_descriptor.dstaddr = (uint32_t)_adc_buf_0 + sizeof(uint16_t) * ADC_BUF_LEN; // Place it in the adc_buf_0 array
|
||||
_descriptor.btcnt = ADC_BUF_LEN; // Beat count
|
||||
_descriptor.btctrl = DMAC_BTCTRL_BEATSIZE_HWORD | // Beat size is HWORD (16-bits)
|
||||
DMAC_BTCTRL_DSTINC | // Increment the destination address
|
||||
DMAC_BTCTRL_VALID | // Descriptor is valid
|
||||
DMAC_BTCTRL_BLOCKACT_SUSPEND; // Suspend DMAC channel 0 after block transfer
|
||||
memcpy(&_descriptor_section[0], &_descriptor, sizeof(_descriptor)); // Copy the descriptor to the descriptor section
|
||||
|
||||
_descriptor.descaddr = (uint32_t)&_descriptor_section[0]; // Set up a circular descriptor
|
||||
_descriptor.srcaddr = (uint32_t)&ADC1->RESULT.reg; // Take the result from the ADC0 RESULT register
|
||||
_descriptor.dstaddr = (uint32_t)_adc_buf_1 + sizeof(uint16_t) * ADC_BUF_LEN; // Place it in the adc_buf_1 array
|
||||
_descriptor.btcnt = ADC_BUF_LEN; // Beat count
|
||||
_descriptor.btctrl = DMAC_BTCTRL_BEATSIZE_HWORD | // Beat size is HWORD (16-bits)
|
||||
DMAC_BTCTRL_DSTINC | // Increment the destination address
|
||||
DMAC_BTCTRL_VALID | // Descriptor is valid
|
||||
DMAC_BTCTRL_BLOCKACT_SUSPEND; // Suspend DMAC channel 0 after block transfer
|
||||
memcpy(&_descriptor_section[1], &_descriptor, sizeof(_descriptor)); // Copy the descriptor to the descriptor section
|
||||
|
||||
// Configure NVIC
|
||||
NVIC_SetPriority(DMAC_1_IRQn, 0); // Set the Nested Vector Interrupt Controller (NVIC) priority for DMAC1 to 0 (highest)
|
||||
NVIC_EnableIRQ(DMAC_1_IRQn); // Connect DMAC1 to Nested Vector Interrupt Controller (NVIC)
|
||||
|
||||
// Activate the suspend (SUSP) interrupt on DMAC channel 1
|
||||
DMAC->Channel[1].CHINTENSET.reg = DMAC_CHINTENSET_SUSP;
|
||||
|
||||
// Configure ADC
|
||||
ADC1->INPUTCTRL.bit.MUXPOS = ADC_INPUTCTRL_MUXPOS_AIN12_Val; // Set the analog input to ADC0/AIN2 (PB08 - A4 on Metro M4)
|
||||
while (ADC1->SYNCBUSY.bit.INPUTCTRL)
|
||||
; // Wait for synchronization
|
||||
ADC1->SAMPCTRL.bit.SAMPLEN = 0x00; // Set max Sampling Time Length to half divided ADC clock pulse (2.66us)
|
||||
while (ADC1->SYNCBUSY.bit.SAMPCTRL)
|
||||
; // Wait for synchronization
|
||||
ADC1->CTRLA.reg = ADC_CTRLA_PRESCALER_DIV128; // Divide Clock ADC GCLK by 128 (48MHz/128 = 375kHz)
|
||||
ADC1->CTRLB.reg = ADC_CTRLB_RESSEL_12BIT | // Set ADC resolution to 12 bits
|
||||
ADC_CTRLB_FREERUN; // Set ADC to free run mode
|
||||
while (ADC1->SYNCBUSY.bit.CTRLB)
|
||||
; // Wait for synchronization
|
||||
ADC1->CTRLA.bit.ENABLE = 1; // Enable the ADC
|
||||
while (ADC1->SYNCBUSY.bit.ENABLE)
|
||||
; // Wait for synchronization
|
||||
ADC1->SWTRIG.bit.START = 1; // Initiate a software trigger to start an ADC conversion
|
||||
while (ADC1->SYNCBUSY.bit.SWTRIG)
|
||||
; // Wait for synchronization
|
||||
|
||||
// Enable DMA channel 1
|
||||
DMAC->Channel[1].CHCTRLA.bit.ENABLE = 1;
|
||||
|
||||
// Configure Timer/Counter 5
|
||||
GCLK->PCHCTRL[TC5_GCLK_ID].reg = GCLK_PCHCTRL_CHEN | // Enable perhipheral channel for TC5
|
||||
GCLK_PCHCTRL_GEN_GCLK1; // Connect generic clock 0 at 48MHz
|
||||
|
||||
TC5->COUNT16.WAVE.reg = TC_WAVE_WAVEGEN_MFRQ; // Set TC5 to Match Frequency (MFRQ) mode
|
||||
TC5->COUNT16.CC[0].reg = 3000 - 1; // Set the trigger to 16 kHz: (4Mhz / 16000) - 1
|
||||
while (TC5->COUNT16.SYNCBUSY.bit.CC0)
|
||||
; // Wait for synchronization
|
||||
|
||||
// Start Timer/Counter 5
|
||||
TC5->COUNT16.CTRLA.bit.ENABLE = 1; // Enable the TC5 timer
|
||||
while (TC5->COUNT16.SYNCBUSY.bit.ENABLE)
|
||||
; // Wait for synchronization
|
||||
}
|
||||
|
||||
uint16_t _adc_buf_0[ADC_BUF_LEN];
|
||||
uint16_t _adc_buf_1[ADC_BUF_LEN];
|
||||
|
||||
// WAV files have a header. This struct defines that header
|
||||
struct wavFileHeader
|
||||
{
|
||||
char riff[4]; /* "RIFF" */
|
||||
long flength; /* file length in bytes */
|
||||
char wave[4]; /* "WAVE" */
|
||||
char fmt[4]; /* "fmt " */
|
||||
long chunk_size; /* size of FMT chunk in bytes (usually 16) */
|
||||
short format_tag; /* 1=PCM, 257=Mu-Law, 258=A-Law, 259=ADPCM */
|
||||
short num_chans; /* 1=mono, 2=stereo */
|
||||
long srate; /* Sampling rate in samples per second */
|
||||
long bytes_per_sec; /* bytes per second = srate*bytes_per_samp */
|
||||
short bytes_per_samp; /* 2=16-bit mono, 4=16-bit stereo */
|
||||
short bits_per_samp; /* Number of bits per sample */
|
||||
char data[4]; /* "data" */
|
||||
long dlength; /* data length in bytes (filelength - 44) */
|
||||
};
|
||||
|
||||
void initBufferHeader()
|
||||
{
|
||||
wavFileHeader wavh;
|
||||
|
||||
strncpy(wavh.riff, "RIFF", 4);
|
||||
strncpy(wavh.wave, "WAVE", 4);
|
||||
strncpy(wavh.fmt, "fmt ", 4);
|
||||
strncpy(wavh.data, "data", 4);
|
||||
|
||||
wavh.chunk_size = 16;
|
||||
wavh.format_tag = 1; // PCM
|
||||
wavh.num_chans = 1; // mono
|
||||
wavh.srate = RATE;
|
||||
wavh.bytes_per_sec = (RATE * 1 * 16 * 1) / 8;
|
||||
wavh.bytes_per_samp = 2;
|
||||
wavh.bits_per_samp = 16;
|
||||
wavh.dlength = RATE * 2 * 1 * 16 / 2;
|
||||
wavh.flength = wavh.dlength + 44;
|
||||
|
||||
_writer.writeSfudBuffer((byte *)&wavh, 44);
|
||||
}
|
||||
|
||||
void audioCallback(uint16_t *buf, uint32_t buf_len)
|
||||
{
|
||||
static uint32_t idx = 44;
|
||||
|
||||
if (_isRecording)
|
||||
{
|
||||
for (uint32_t i = 0; i < buf_len; i++)
|
||||
{
|
||||
int16_t audio_value = ((int16_t)buf[i] - 2048) * 16;
|
||||
|
||||
_writer.writeSfudBuffer(audio_value & 0xFF);
|
||||
_writer.writeSfudBuffer((audio_value >> 8) & 0xFF);
|
||||
}
|
||||
|
||||
idx += buf_len;
|
||||
|
||||
if (idx >= BUFFER_SIZE)
|
||||
{
|
||||
_writer.flushSfudBuffer();
|
||||
idx = 44;
|
||||
_isRecording = false;
|
||||
_isRecordingReady = true;
|
||||
}
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
Mic mic;
|
||||
|
||||
void DMAC_1_Handler()
|
||||
{
|
||||
mic.dmaHandler();
|
||||
}
|
@ -0,0 +1,102 @@
|
||||
#pragma once
|
||||
|
||||
#include <Arduino.h>
|
||||
#include <ArduinoJson.h>
|
||||
#include <HTTPClient.h>
|
||||
#include <WiFiClientSecure.h>
|
||||
|
||||
#include "config.h"
|
||||
#include "flash_stream.h"
|
||||
|
||||
class SpeechToText
|
||||
{
|
||||
public:
|
||||
void init()
|
||||
{
|
||||
_token_client.setCACert(TOKEN_CERTIFICATE);
|
||||
_speech_client.setCACert(SPEECH_CERTIFICATE);
|
||||
_access_token = getAccessToken();
|
||||
}
|
||||
|
||||
String convertSpeechToText()
|
||||
{
|
||||
char url[128];
|
||||
sprintf(url, SPEECH_URL, SPEECH_LOCATION, LANGUAGE);
|
||||
|
||||
HTTPClient httpClient;
|
||||
httpClient.begin(_speech_client, url);
|
||||
|
||||
httpClient.addHeader("Authorization", String("Bearer ") + _access_token);
|
||||
httpClient.addHeader("Content-Type", String("audio/wav; codecs=audio/pcm; samplerate=") + String(RATE));
|
||||
httpClient.addHeader("Accept", "application/json;text/xml");
|
||||
|
||||
Serial.println("Sending speech...");
|
||||
|
||||
FlashStream stream;
|
||||
int httpResponseCode = httpClient.sendRequest("POST", &stream, BUFFER_SIZE);
|
||||
|
||||
Serial.println("Speech sent!");
|
||||
|
||||
String text = "";
|
||||
|
||||
if (httpResponseCode == 200)
|
||||
{
|
||||
String result = httpClient.getString();
|
||||
Serial.println(result);
|
||||
|
||||
DynamicJsonDocument doc(1024);
|
||||
deserializeJson(doc, result.c_str());
|
||||
|
||||
JsonObject obj = doc.as<JsonObject>();
|
||||
text = obj["DisplayText"].as<String>();
|
||||
}
|
||||
else if (httpResponseCode == 401)
|
||||
{
|
||||
Serial.println("Access token expired, trying again with a new token");
|
||||
_access_token = getAccessToken();
|
||||
return convertSpeechToText();
|
||||
}
|
||||
else
|
||||
{
|
||||
Serial.print("Failed to convert text to speech - error ");
|
||||
Serial.println(httpResponseCode);
|
||||
}
|
||||
|
||||
httpClient.end();
|
||||
|
||||
return text;
|
||||
}
|
||||
|
||||
private:
|
||||
String getAccessToken()
|
||||
{
|
||||
char url[128];
|
||||
sprintf(url, TOKEN_URL, SPEECH_LOCATION);
|
||||
|
||||
HTTPClient httpClient;
|
||||
httpClient.begin(_token_client, url);
|
||||
|
||||
httpClient.addHeader("Ocp-Apim-Subscription-Key", SPEECH_API_KEY);
|
||||
int httpResultCode = httpClient.POST("{}");
|
||||
|
||||
if (httpResultCode != 200)
|
||||
{
|
||||
Serial.println("Error getting access token, trying again...");
|
||||
delay(10000);
|
||||
return getAccessToken();
|
||||
}
|
||||
|
||||
Serial.println("Got access token.");
|
||||
String result = httpClient.getString();
|
||||
|
||||
httpClient.end();
|
||||
|
||||
return result;
|
||||
}
|
||||
|
||||
WiFiClientSecure _token_client;
|
||||
WiFiClientSecure _speech_client;
|
||||
String _access_token;
|
||||
};
|
||||
|
||||
SpeechToText speechToText;
|
@ -0,0 +1,86 @@
|
||||
#pragma once
|
||||
|
||||
#include <Arduino.h>
|
||||
#include <ArduinoJson.h>
|
||||
#include <HTTPClient.h>
|
||||
#include <Seeed_FS.h>
|
||||
#include <SD/Seeed_SD.h>
|
||||
#include <WiFiClient.h>
|
||||
#include <WiFiClientSecure.h>
|
||||
|
||||
#include "config.h"
|
||||
|
||||
class TextToSpeech
|
||||
{
|
||||
public:
|
||||
void init()
|
||||
{
|
||||
DynamicJsonDocument doc(1024);
|
||||
doc["language"] = LANGUAGE;
|
||||
|
||||
String body;
|
||||
serializeJson(doc, body);
|
||||
|
||||
HTTPClient httpClient;
|
||||
httpClient.begin(_client, GET_VOICES_FUNCTION_URL);
|
||||
|
||||
int httpResponseCode = httpClient.POST(body);
|
||||
|
||||
if (httpResponseCode == 200)
|
||||
{
|
||||
String result = httpClient.getString();
|
||||
Serial.println(result);
|
||||
|
||||
DynamicJsonDocument doc(1024);
|
||||
deserializeJson(doc, result.c_str());
|
||||
|
||||
JsonArray obj = doc.as<JsonArray>();
|
||||
_voice = obj[0].as<String>();
|
||||
|
||||
Serial.print("Using voice ");
|
||||
Serial.println(_voice);
|
||||
}
|
||||
else
|
||||
{
|
||||
Serial.print("Failed to get voices - error ");
|
||||
Serial.println(httpResponseCode);
|
||||
}
|
||||
|
||||
httpClient.end();
|
||||
}
|
||||
|
||||
void convertTextToSpeech(String text)
|
||||
{
|
||||
DynamicJsonDocument doc(1024);
|
||||
doc["language"] = LANGUAGE;
|
||||
doc["voice"] = _voice;
|
||||
doc["text"] = text;
|
||||
|
||||
String body;
|
||||
serializeJson(doc, body);
|
||||
|
||||
HTTPClient httpClient;
|
||||
httpClient.begin(_client, TEXT_TO_SPEECH_FUNCTION_URL);
|
||||
|
||||
int httpResponseCode = httpClient.POST(body);
|
||||
|
||||
if (httpResponseCode == 200)
|
||||
{
|
||||
File wav_file = SD.open("SPEECH.WAV", FILE_WRITE);
|
||||
httpClient.writeToStream(&wav_file);
|
||||
wav_file.close();
|
||||
}
|
||||
else
|
||||
{
|
||||
Serial.print("Failed to get speech - error ");
|
||||
Serial.println(httpResponseCode);
|
||||
}
|
||||
|
||||
httpClient.end();
|
||||
}
|
||||
private:
|
||||
WiFiClient _client;
|
||||
String _voice;
|
||||
};
|
||||
|
||||
TextToSpeech textToSpeech;
|
@ -0,0 +1,58 @@
|
||||
#pragma once
|
||||
|
||||
#include <Arduino.h>
|
||||
#include <ArduinoJson.h>
|
||||
#include <HTTPClient.h>
|
||||
#include <WiFiClient.h>
|
||||
|
||||
#include "config.h"
|
||||
|
||||
class TextTranslator
|
||||
{
|
||||
public:
|
||||
String translateText(String text, String from_language, String to_language)
|
||||
{
|
||||
DynamicJsonDocument doc(1024);
|
||||
doc["text"] = text;
|
||||
doc["from_language"] = from_language;
|
||||
doc["to_language"] = to_language;
|
||||
|
||||
String body;
|
||||
serializeJson(doc, body);
|
||||
|
||||
Serial.print("Translating ");
|
||||
Serial.print(text);
|
||||
Serial.print(" from ");
|
||||
Serial.print(from_language);
|
||||
Serial.print(" to ");
|
||||
Serial.println(to_language);
|
||||
|
||||
HTTPClient httpClient;
|
||||
httpClient.begin(_client, TRANSLATE_FUNCTION_URL);
|
||||
|
||||
int httpResponseCode = httpClient.POST(body);
|
||||
|
||||
String translated_text = "";
|
||||
|
||||
if (httpResponseCode == 200)
|
||||
{
|
||||
translated_text = httpClient.getString();
|
||||
Serial.print("Translated: ");
|
||||
Serial.println(translated_text);
|
||||
}
|
||||
else
|
||||
{
|
||||
Serial.print("Failed to translate text - error ");
|
||||
Serial.println(httpResponseCode);
|
||||
}
|
||||
|
||||
httpClient.end();
|
||||
|
||||
return translated_text;
|
||||
}
|
||||
|
||||
private:
|
||||
WiFiClient _client;
|
||||
};
|
||||
|
||||
TextTranslator textTranslator;
|
@ -0,0 +1,11 @@
|
||||
|
||||
This directory is intended for PlatformIO Unit Testing and project tests.
|
||||
|
||||
Unit Testing is a software testing method by which individual units of
|
||||
source code, sets of one or more MCU program modules together with associated
|
||||
control data, usage procedures, and operating procedures, are tested to
|
||||
determine whether they are fit for use. Unit testing finds problems early
|
||||
in the development cycle.
|
||||
|
||||
More information about PlatformIO Unit Testing:
|
||||
- https://docs.platformio.org/page/plus/unit-testing.html
|
@ -1,3 +1,270 @@
|
||||
# Translate speech - Wio Terminal
|
||||
|
||||
Coming soon!
|
||||
In this part of the lesson, you will write code to translate text using the translator service.
|
||||
|
||||
## Convert text to speech using the translator service
|
||||
|
||||
The speech service REST API doesn't support direct translations, instead you can use the Translator service to translate the text generated by the speech to text service, and the text of the spoken response. This service has a REST API you can use to translate the text, but to make it easier to use this will be wrapped in another HTTP trigger in your functions app.
|
||||
|
||||
### Task - create a serverless function to translate text
|
||||
|
||||
1. Open your `smart-timer-trigger` project in VS Code, and open the terminal ensuring the virtual environment is activated. If not, kill and re-create the terminal.
|
||||
|
||||
1. Open the `local.settings.json` file and add settings for the translator API key and location:
|
||||
|
||||
```json
|
||||
"TRANSLATOR_KEY": "<key>",
|
||||
"TRANSLATOR_LOCATION": "<location>"
|
||||
```
|
||||
|
||||
Replace `<key>` with the API key for your translator service resource. Replace `<location>` with the location you used when you created the translator service resource.
|
||||
|
||||
1. Add a new HTTP trigger to this app called `translate-text` using the following command from inside the VS Code terminal in the root folder of the functions app project:
|
||||
|
||||
```sh
|
||||
func new --name translate-text --template "HTTP trigger"
|
||||
```
|
||||
|
||||
This will create an HTTP trigger called `translate-text`.
|
||||
|
||||
1. Replace the contents of the `__init__.py` file in the `translate-text` folder with the following:
|
||||
|
||||
```python
|
||||
import logging
|
||||
import os
|
||||
import requests
|
||||
|
||||
import azure.functions as func
|
||||
|
||||
location = os.environ['TRANSLATOR_LOCATION']
|
||||
translator_key = os.environ['TRANSLATOR_KEY']
|
||||
|
||||
def main(req: func.HttpRequest) -> func.HttpResponse:
|
||||
req_body = req.get_json()
|
||||
from_language = req_body['from_language']
|
||||
to_language = req_body['to_language']
|
||||
text = req_body['text']
|
||||
|
||||
logging.info(f'Translating {text} from {from_language} to {to_language}')
|
||||
|
||||
url = f'https://api.cognitive.microsofttranslator.com/translate?api-version=3.0'
|
||||
|
||||
headers = {
|
||||
'Ocp-Apim-Subscription-Key': translator_key,
|
||||
'Ocp-Apim-Subscription-Region': location,
|
||||
'Content-type': 'application/json'
|
||||
}
|
||||
|
||||
params = {
|
||||
'from': from_language,
|
||||
'to': to_language
|
||||
}
|
||||
|
||||
body = [{
|
||||
'text' : text
|
||||
}]
|
||||
|
||||
response = requests.post(url, headers=headers, params=params, json=body)
|
||||
return func.HttpResponse(response.json()[0]['translations'][0]['text'])
|
||||
```
|
||||
|
||||
This code extracts the text and the languages from the HTTP request. It then makes a request to the translator REST API, passing the languages as parameters for the URL and the text to translate as the body. Finally, the translation is returned.
|
||||
|
||||
1. Run your function app locally. You can then call this using a tool like curl in the same way that you tested your `text-to-timer` HTTP trigger. Make sure to pass the text to translate and the languages as a JSON body:
|
||||
|
||||
```json
|
||||
{
|
||||
"text": "Définir une minuterie de 30 secondes",
|
||||
"from_language": "fr-FR",
|
||||
"to_language": "en-US"
|
||||
}
|
||||
```
|
||||
|
||||
This example translates *Définir une minuterie de 30 secondes* from French to US English. It will return *Set a 30-second timer*.
|
||||
|
||||
> 💁 You can find this code in the [code/functions](code/functions) folder.
|
||||
|
||||
### Task - use the translator function to translate text
|
||||
|
||||
1. Open the `smart-timer` project in VS Code if it is not already open.
|
||||
|
||||
1. Your smart timer will have 2 languages set - the language of the server that was used to train LUIS (the same language is also used to build the messages to speak to the user), and the language spoken by the user. Update the `LANGUAGE` constant in the `config.h` header file to be the language that will be spoken by the user, and add a new constant called `SERVER_LANGUAGE` for the language used to train LUIS:
|
||||
|
||||
```cpp
|
||||
const char *LANGUAGE = "<user language>";
|
||||
const char *SERVER_LANGUAGE = "<server language>";
|
||||
```
|
||||
|
||||
Replace `<user language>` with the locale name for language you will be speaking in, for example `fr-FR` for French, or `zn-HK` for Cantonese.
|
||||
|
||||
Replace `<server language>` with the locale name for language used to train LUIS.
|
||||
|
||||
You can find a list of the supported languages and their locale names in the [Language and voice support documentation on Microsoft docs](https://docs.microsoft.com/azure/cognitive-services/speech-service/language-support?WT.mc_id=academic-17441-jabenn#speech-to-text).
|
||||
|
||||
> 💁 If you don't speak multiple languages you can use a service like [Bing Translate](https://www.bing.com/translator) or [Google Translate](https://translate.google.com) to translate from your preferred language to a language of your choice. These services can then play audio of the translated text.
|
||||
>
|
||||
> For example, if you train LUIS in English, but want to use French as the user language, you can translate sentences like "set a 2 minute and 27 second timer" from English into French using Bing Translate, then use the **Listen translation** button to speak the translation into your microphone.
|
||||
>
|
||||
> 
|
||||
|
||||
1. Add the translator API key and location below the `SPEECH_LOCATION`:
|
||||
|
||||
```cpp
|
||||
const char *TRANSLATOR_API_KEY = "<KEY>";
|
||||
const char *TRANSLATOR_LOCATION = "<LOCATION>";
|
||||
```
|
||||
|
||||
Replace `<KEY>` with the API key for your translator service resource. Replace `<LOCATION>` with the location you used when you created the translator service resource.
|
||||
|
||||
1. Add the translator trigger URL below the `VOICE_URL`:
|
||||
|
||||
```cpp
|
||||
const char *TRANSLATE_FUNCTION_URL = "<URL>";
|
||||
```
|
||||
|
||||
Replace `<URL>` with the URL for the `translate-text` HTTP trigger on your function app. This will be the same as the value for `TEXT_TO_TIMER_FUNCTION_URL`, except with a function name of `translate-text` instead of `text-to-timer`.
|
||||
|
||||
1. Add a new file to the `src` folder called `text_translator.h`.
|
||||
|
||||
1. This new `text_translator.h` header file will contain a class to translate text. Add the following to this file to declare this class:
|
||||
|
||||
```cpp
|
||||
#pragma once
|
||||
|
||||
#include <Arduino.h>
|
||||
#include <ArduinoJson.h>
|
||||
#include <HTTPClient.h>
|
||||
#include <WiFiClient.h>
|
||||
|
||||
#include "config.h"
|
||||
|
||||
class TextTranslator
|
||||
{
|
||||
public:
|
||||
private:
|
||||
WiFiClient _client;
|
||||
};
|
||||
|
||||
TextTranslator textTranslator;
|
||||
```
|
||||
|
||||
This declares the `TextTranslator` class, along with an instance of this class. The class has a single field for the WiFi client.
|
||||
|
||||
1. To the `public` section of this class, add a method to translate text:
|
||||
|
||||
```cpp
|
||||
String translateText(String text, String from_language, String to_language)
|
||||
{
|
||||
}
|
||||
```
|
||||
|
||||
This method takes the language to translate from, and the language to translate to. When handling speech, the speech will be translated from the user language to the LUIS server language, and when giving responses it will translate from the LUIS server language to the users language.
|
||||
|
||||
1. In this method, add code to construct a JSON body containing the text to translate and the languages:
|
||||
|
||||
```cpp
|
||||
DynamicJsonDocument doc(1024);
|
||||
doc["text"] = text;
|
||||
doc["from_language"] = from_language;
|
||||
doc["to_language"] = to_language;
|
||||
|
||||
String body;
|
||||
serializeJson(doc, body);
|
||||
|
||||
Serial.print("Translating ");
|
||||
Serial.print(text);
|
||||
Serial.print(" from ");
|
||||
Serial.print(from_language);
|
||||
Serial.print(" to ");
|
||||
Serial.print(to_language);
|
||||
```
|
||||
|
||||
1. Below this, add the following code to send the body to the serverless function app:
|
||||
|
||||
```cpp
|
||||
HTTPClient httpClient;
|
||||
httpClient.begin(_client, TRANSLATE_FUNCTION_URL);
|
||||
|
||||
int httpResponseCode = httpClient.POST(body);
|
||||
```
|
||||
|
||||
1. Next, add code to get the response:
|
||||
|
||||
```cpp
|
||||
String translated_text = "";
|
||||
|
||||
if (httpResponseCode == 200)
|
||||
{
|
||||
translated_text = httpClient.getString();
|
||||
Serial.print("Translated: ");
|
||||
Serial.println(translated_text);
|
||||
}
|
||||
else
|
||||
{
|
||||
Serial.print("Failed to translate text - error ");
|
||||
Serial.println(httpResponseCode);
|
||||
}
|
||||
```
|
||||
|
||||
1. Finally, add code to close the connection and return the translated text:
|
||||
|
||||
```cpp
|
||||
httpClient.end();
|
||||
|
||||
return translated_text;
|
||||
```
|
||||
|
||||
### Task - translate the recognized speech and the responses
|
||||
|
||||
1. Open the `main.cpp` file.
|
||||
|
||||
1. Add an include directive at the top of the file for the `TextTranslator` class header file:
|
||||
|
||||
```cpp
|
||||
#include "text_translator.h"
|
||||
```
|
||||
|
||||
1. The text that is said when a timer is set or expires needs to be translated. To do this, add the following as the first line of the `say` function:
|
||||
|
||||
```cpp
|
||||
text = textTranslator.translateText(text, LANGUAGE, SERVER_LANGUAGE);
|
||||
```
|
||||
|
||||
This will translate the text to the users language.
|
||||
|
||||
1. In the `processAudio` function, text is retrieved from the captured audio with the `String text = speechToText.convertSpeechToText();` call. After this call, translate the text:
|
||||
|
||||
```cpp
|
||||
String text = speechToText.convertSpeechToText();
|
||||
text = textTranslator.translateText(text, LANGUAGE, SERVER_LANGUAGE);
|
||||
```
|
||||
|
||||
This will translate the text from the users language into the language used on the server.
|
||||
|
||||
1. Build this code, upload it to your Wio Terminal and test it out through the serial monitor. Once you see `Ready` in the serial monitor, press the C button (the one on the left-hand side, closest to the power switch), and speak. Ensure your function app is running, and request a timer in the user language, either by speaking that language yourself, or using a translation app.
|
||||
|
||||
```output
|
||||
Connecting to WiFi..
|
||||
Connected!
|
||||
Got access token.
|
||||
Ready.
|
||||
Starting recording...
|
||||
Finished recording
|
||||
Sending speech...
|
||||
Speech sent!
|
||||
{"RecognitionStatus":"Success","DisplayText":"Définir une minuterie de 2 minutes 27 secondes.","Offset":9600000,"Duration":40400000}
|
||||
Translating Définir une minuterie de 2 minutes 27 secondes. from fr-FR to en-US
|
||||
Translated: Set a timer of 2 minutes 27 seconds.
|
||||
Set a timer of 2 minutes 27 seconds.
|
||||
{"seconds": 147}
|
||||
Translating 2 minute 27 second timer started. from en-US to fr-FR
|
||||
Translated: 2 minute 27 seconde minute a commencé.
|
||||
2 minute 27 seconde minute a commencé.
|
||||
Translating Times up on your 2 minute 27 second timer. from en-US to fr-FR
|
||||
Translated: Chronométrant votre minuterie de 2 minutes 27 secondes.
|
||||
Chronométrant votre minuterie de 2 minutes 27 secondes.
|
||||
```
|
||||
|
||||
> 💁 You can find this code in the [code/wio-terminal](code/wio-terminal) folder.
|
||||
|
||||
😀 Your multi-lingual timer program was a success!
|
||||
|
Binary file not shown.
After Width: | Height: | Size: 514 KiB |
Loading…
Reference in new issue